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

    Neuronpedia

    INDEX
    Explanations

    phrases that define or describe concepts, often with a formal or evaluative tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     auft
    -0.59
    assioned
    -0.56
    Afri
    -0.53
    шеб
    -0.53
    发表于
    -0.52
    たて
    -0.52
    تعداد
    -0.51
     fprintf
    -0.51
     mortes
    -0.50
     cím
    -0.50
    POSITIVE LOGITS
     étant
    0.88
     being
    0.84
     fiind
    0.82
     having
    0.76
    Smarty
    0.72
    being
    0.72
     مشين
    0.67
    having
    0.66
    DrawerToggle
    0.66
     sendo
    0.64
    Act Density 0.288%

    No Known Activations