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

    Neuronpedia

    INDEX
    Explanations

    descriptions of significance or quality related to entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noDo
    -0.40
     certain
    -0.35
    WriteAttribute
    -0.35
    municipi
    -0.35
     aantal
    -0.33
    protoc
    -0.32
    MockBean
    -0.30
    webElementXpaths
    -0.30
     yet
    -0.30
     bestimm
    -0.30
    POSITIVE LOGITS
    matter
    0.79
     matter
    0.77
     privilege
    0.75
    privilege
    0.73
     blessing
    0.73
    pleasure
    0.72
     moot
    0.72
     bummer
    0.71
     shame
    0.69
     gamble
    0.69
    Act Density 0.346%

    No Known Activations