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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.82
     raiſ
    -0.77
     Eſ
    -0.73
     Antal
    -0.71
     $_"
    -0.70
     Ambro
    -0.70
    ſelf
    -0.70
     AppColors
    -0.69
     ―――――
    -0.69
    ReusableCell
    -0.68
    POSITIVE LOGITS
     then
    0.67
     it
    0.65
     certainly
    0.57
     shouldn
    0.57
     should
    0.55
     don
    0.55
     thì
    0.54
     only
    0.53
     can
    0.51
     definitely
    0.51
    Act Density 0.289%

    No Known Activations