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

    Neuronpedia

    INDEX
    Explanations

    technical terms and symbols related to mathematical or logical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McIntyre
    -0.85
     ")");
    -0.74
    miary
    -0.69
    mew
    -0.69
    iyaki
    -0.67
     Paola
    -0.65
    siąż
    -0.65
     newNode
    -0.64
     Stoll
    -0.63
     Smy
    -0.63
    POSITIVE LOGITS
    {~
    0.91
     فريبيس
    0.91
    {{\
    0.81
    }{
    0.78
    </strong>
    0.77
     }^{[
    0.75
     defaultstate
    0.75
    {{{
    0.75
    ={[
    0.74
     gynhyrchwyd
    0.74
    Act Density 1.428%

    No Known Activations