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

    Neuronpedia

    INDEX
    Explanations

    blocks or sections of code denoted by curly braces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spesies
    -0.79
    hésite
    -0.78
     defaultstate
    -0.76
    tonsoft
    -0.71
    mybatisplus
    -0.69
    gridad
    -0.66
    GenerationType
    -0.65
    atalytic
    -0.65
     contextLoads
    -0.64
    Hochspringen
    -0.63
    POSITIVE LOGITS
     {
    0.71
    ::{
    0.70
     {
    0.59
     import
    0.55
    ^{-}\
    0.48
    </em>
    0.47
    Referanser
    0.46
     If
    0.45
    <strong>
    0.45
    yl
    0.45
    Act Density 0.058%

    No Known Activations