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

    Neuronpedia

    INDEX
    Explanations

    hyphenated terms indicating a time-related concept or action

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related concepts and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.76
     Flavoring
    -0.73
     Voice
    -0.67
     Poe
    -0.64
     EntityItem
    -0.63
     Alb
    -0.62
     Seg
    -0.61
    enza
    -0.61
     Fla
    -0.60
     xp
    -0.60
    POSITIVE LOGITS
    consuming
    1.49
    hon
    1.39
    travel
    1.33
    tested
    1.28
    saving
    1.17
    sensitive
    1.16
    delay
    1.15
    trial
    1.13
    limit
    1.11
    share
    1.10
    Act Density 0.044%

    No Known Activations