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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating doubt or lack of certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]='\
    -0.77
    AutoField
    -0.73
    unhofer
    -0.71
     AspNetCore
    -0.70
    ⓧ
    -0.69
    而非
    -0.66
    ]--;
    -0.65
    OGND
    -0.63
    +#+
    -0.63
     autorytatywna
    -0.61
    POSITIVE LOGITS
     nor
    0.98
     tampoco
    0.66
     sondern
    0.65
     either
    0.63
    Nor
    0.61
    nor
    0.59
     nici
    0.58
     Nor
    0.56
     esencia
    0.54
     whatsoever
    0.54
    Act Density 0.326%

    No Known Activations