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

    Neuronpedia

    INDEX
    Explanations

    references to user interface elements and alert systems in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.57
     Le
    -0.56
     in
    -0.55
     the
    -0.54
     if
    -0.54
     Val
    -0.53
     pass
    -0.51
     of
    -0.51
     A
    -0.50
    '][$
    -0.49
    POSITIVE LOGITS
    ArgsConstructor
    0.88
     صوتيه
    0.83
     ſta
    0.83
     ſche
    0.82
    ViewFeatures
    0.81
     Италијани
    0.80
     paramInt
    0.79
     Efq
    0.79
     Jefus
    0.79
    oneofs
    0.79
    Act Density 0.093%

    No Known Activations