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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptionality or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     photolibrary
    -0.70
    קישורים
    -0.69
     Hermitage
    -0.69
     Sarm
    -0.68
     NSCoder
    -0.68
     >=",
    -0.68
     Jefus
    -0.67
    ArgsConstructor
    -0.67
    engkapnya
    -0.66
     Normdatei
    -0.66
    POSITIVE LOGITS
     sauf
    0.62
     
    0.58
     except
    0.54
     including
    0.54
     "
    0.53
    YTE
    0.53
     Except
    0.53
     del
    0.52
    .
    0.51
     Not
    0.50
    Act Density 0.326%

    No Known Activations