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

    Neuronpedia

    INDEX
    Explanations

    organizations and agreements

    oai_token-act-pair · gpt-3.5-turbo

    the presence of organizational abbreviations or acronyms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     impe
    -0.79
     lyr
    -0.78
     haunted
    -0.77
     baffled
    -0.76
     blot
    -0.76
     lull
    -0.76
     contempor
    -0.75
     incons
    -0.74
     drift
    -0.74
     depress
    -0.73
    POSITIVE LOGITS
    formerly
    1.26
    sic
    1.25
    aka
    1.24
    including
    1.18
    ADA
    1.09
    excluding
    1.08
    see
    1.07
    UGC
    1.05
    PDF
    1.04
    also
    1.03
    Act Density 0.109%

    No Known Activations