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

    Neuronpedia

    INDEX
    Explanations

    references to specific time periods or historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference "days" in a nostalgic or temporal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emort
    -0.72
    Leaks
    -0.68
    edly
    -0.68
    ItemTracker
    -0.67
    acted
    -0.64
    Lex
    -0.64
    Americ
    -0.64
     Masquerade
    -0.63
    emale
    -0.63
     RELEASE
    -0.63
    POSITIVE LOGITS
    pring
    1.14
    hift
    1.03
    creen
    1.00
    pread
    0.93
    dream
    0.86
    paces
    0.78
    cript
    0.77
    cale
    0.74
    days
    0.71
    ult
    0.70
    Act Density 0.041%

    No Known Activations