Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    relationships and actions involving change and transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    modal verbs followed by main verbs, particularly phrases indicating ability or potential like "can do" or "could be".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    phrases expressing effort, capability, or doing one's best in completing a task or goal.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    ########.
    -0.73
    sizeCache
    -0.63
    TagMode
    -0.63
    CloseOperation
    -0.60
     betweenstory
    -0.59
    ScopeManager
    -0.56
    WriteTagHelper
    -0.56
     препратки
    -0.55
     CascadeType
    -0.52
    rzost
    -0.52
    POSITIVE LOGITS
     câte
    0.38
     betreffende
    0.35
     hábiles
    0.33
     mergeFrom
    0.33
     without
    0.32
     rospy
    0.32
     endereco
    0.32
     fără
    0.31
     ponieważ
    0.31
     atteinte
    0.31
    Act Density 0.497%

    No Known Activations