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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions and scheduling information

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numerical designations or street addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tradem
    -0.85
    inates
    -0.78
    abwe
    -0.72
    uations
    -0.70
    kens
    -0.67
    pmwiki
    -0.66
    inate
    -0.62
    kes
    -0.61
    aution
    -0.61
    hement
    -0.61
    POSITIVE LOGITS
    87
    0.98
    th
    0.95
    50
    0.93
    88
    0.91
    01
    0.91
    77
    0.91
    61
    0.91
    66
    0.90
    37
    0.88
    81
    0.88
    Act Density 0.048%

    No Known Activations