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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences with emphasis on a particular quality or aspect

    oai_token-act-pair · gpt-3.5-turbo

    demonstratives and references to specific concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Footnote
    -0.79
    letters
    -0.72
    OUND
    -0.66
    AUD
    -0.66
    wcsstore
    -0.65
     Voices
    -0.63
    aws
    -0.62
     Altern
    -0.62
     excerpts
    -0.62
    YR
    -0.61
    POSITIVE LOGITS
     much
    1.22
     way
    1.14
     far
    0.99
    much
    0.97
     cheaply
    0.95
     badly
    0.93
     easily
    0.93
     magnitude
    0.89
     MUCH
    0.89
     kind
    0.87
    Act Density 0.090%

    No Known Activations