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

    Neuronpedia

    INDEX
    Explanations

    words related to multiple scenarios and topics without a specific theme

    oai_token-act-pair · gpt-3.5-turbo

    the plural forms of nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.71
    adium
    -0.70
     attribution
    -0.70
    atever
    -0.69
    thia
    -0.67
    Reviewer
    -0.66
    Oracle
    -0.64
    acia
    -0.64
    ivities
    -0.63
    èª
    -0.63
    POSITIVE LOGITS
    ystem
    1.00
    eries
    0.90
    pace
    0.89
    cence
    0.85
    omething
    0.83
    poons
    0.80
    peak
    0.78
    hips
    0.76
    paces
    0.74
    hots
    0.73
    Act Density 0.021%

    No Known Activations