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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "know."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    PendingIntent
    -0.76
    IsContent
    -0.62
     Oneida
    -0.58
    InjectAttribute
    -0.58
     disfrut
    -0.58
     Olin
    -0.56
     previa
    -0.56
    TagMode
    -0.55
    enterOuterAlt
    -0.55
     popolo
    -0.54
    POSITIVE LOGITS
    dymyr
    0.81
    yntaxException
    0.79
    󠁿
    0.71
    ArrowToggle
    0.67
    lioz
    0.66
    calo
    0.66
    xase
    0.63
     يتيمه
    0.63
    WAH
    0.63
    emd
    0.62
    Act Density 0.005%

    No Known Activations