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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the action of spreading information or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to dissemination or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deen
    -0.77
    */(
    -0.75
     Zup
    -0.73
    clamation
    -0.68
    herty
    -0.67
    --+
    -0.66
     Starship
    -0.65
     quo
    -0.65
    tarians
    -0.63
     Halls
    -0.61
    POSITIVE LOGITS
    sheets
    1.85
    sheet
    1.41
    shirt
    0.93
     misinformation
    0.91
    pread
    0.83
     spreads
    0.82
     awareness
    0.81
     spread
    0.80
     disinformation
    0.80
     across
    0.80
    Act Density 0.046%

    No Known Activations