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

    Neuronpedia

    INDEX
    Explanations

    highly specific model identifiers or names

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.74
     INTERESAR
    -0.71
     ſche
    -0.66
     fubject
    -0.64
    出版年
    -0.63
     whoſe
    -0.63
    webElementXpaths
    -0.63
     itſelf
    -0.61
     purpoſe
    -0.61
    findpost
    -0.60
    POSITIVE LOGITS
    model
    1.80
     otomatig
    0.65
    principalColumn
    0.63
    controller
    0.60
    chymal
    0.58
    expandindo
    0.57
     '\\;'
    0.57
     مشين
    0.55
    ELTS
    0.54
    mpo
    0.54
    Act Density 0.002%

    No Known Activations