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

    Neuronpedia

    INDEX
    Explanations

    references to public events or activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "demonstration" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saline
    -0.82
    laus
    -0.73
    oho
    -0.73
    esthetic
    -0.64
    olly
    -0.63
    chance
    -0.62
    abol
    -0.62
    missions
    -0.61
    omer
    -0.60
    pop
    -0.60
    POSITIVE LOGITS
     demonstration
    1.09
     demonstrations
    0.91
     GOODMAN
    0.80
     demonstrating
    0.77
     demonstrators
    0.77
    arily
    0.73
    stration
    0.72
     ank
    0.71
    wcsstore
    0.71
     glim
    0.71
    Act Density 0.012%

    No Known Activations