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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to personal experience and perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InSection
    -0.76
    djangoproject
    -0.57
    rzost
    -0.56
    issory
    -0.54
    LEncoder
    -0.54
    sidemargin
    -0.54
    ActionCreators
    -0.53
    AddField
    -0.53
    fjspx
    -0.53
    tagHelperRunner
    -0.53
    POSITIVE LOGITS
     knows
    1.18
     understands
    1.16
     know
    1.05
     understand
    0.97
    know
    0.93
    knows
    0.91
    Knows
    0.85
     Understand
    0.85
    Know
    0.84
     KNOW
    0.84
    Act Density 0.254%

    No Known Activations