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

    Neuronpedia

    INDEX
    Explanations

    statements and references made by individuals in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.54
     (
    -0.53
     Har
    -0.52
    <>();
    -0.52
    }{*}{
    -0.49
     har
    -0.49
     tasca
    -0.48
     for
    -0.47
     Or
    -0.46
     
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.99
    ⓧ
    0.89
     Efq
    0.87
     itſelf
    0.86
     myſelf
    0.82
     kasarigan
    0.82
     Theſe
    0.82
     Roskov
    0.82
    Tikang
    0.81
    aarrggbb
    0.80
    Act Density 0.025%

    No Known Activations