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

    Neuronpedia

    INDEX
    Explanations

    words connected to specific events or scenarios involving actions and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓘ
    -0.58
     disponibilités
    -0.58
     Theſe
    -0.58
    ProgressHUD
    -0.57
    RetentionPolicy
    -0.57
     Shakspeare
    -0.56
     Whom
    -0.54
     فإن
    -0.52
     generality
    -0.51
    onOptions
    -0.51
    POSITIVE LOGITS
     not
    1.22
     still
    1.16
     able
    1.11
     unable
    1.02
     very
    0.99
     quite
    0.93
     considered
    0.90
     a
    0.89
     always
    0.89
     extremely
    0.85
    Act Density 0.742%

    No Known Activations