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

    Neuronpedia

    INDEX
    Explanations

    references to past times or historical periods

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acted
    -0.93
    emort
    -0.90
    acts
    -0.88
    ACTED
    -0.77
    Leaks
    -0.75
    Lex
    -0.74
    Materials
    -0.72
    inav
    -0.71
    iscopal
    -0.70
    ographically
    -0.69
    POSITIVE LOGITS
    pring
    1.17
    creen
    1.04
    hift
    0.98
    cale
    0.95
    pread
    0.84
    dream
    0.83
    days
    0.78
    mith
    0.76
    laus
    0.76
     days
    0.75
    Act Density 0.025%

    No Known Activations