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

    Neuronpedia

    INDEX
    Explanations

    strings that start with "AY" followed by either other letters or numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days, particularly 'day' and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¯
    -0.76
    hered
    -0.73
    arium
    -0.69
    fed
    -0.64
    meg
    -0.61
     Scha
    -0.61
    itia
    -0.60
     priv
    -0.58
     Mamm
    -0.58
     Dresden
    -0.58
    POSITIVE LOGITS
    AY
    1.43
    DAY
    1.09
    WARD
    1.05
    OUT
    1.02
    NESS
    0.97
     GOODMAN
    0.95
    ER
    0.92
    ARY
    0.91
    YY
    0.90
    yip
    0.89
    Act Density 0.003%

    No Known Activations