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

    Neuronpedia

    INDEX
    Explanations

    proper nouns such as names and locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals and their achievements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hov
    -0.71
     [];
    -0.63
    rect
    -0.62
    ategory
    -0.62
     Strauss
    -0.62
    gom
    -0.60
    abetic
    -0.60
     Metatron
    -0.59
    cled
    -0.58
    rought
    -0.58
    POSITIVE LOGITS
     own
    1.18
     debut
    0.87
     OWN
    0.77
     impression
    0.77
    selves
    0.76
     contribution
    0.75
     allowance
    0.75
     displeasure
    0.74
    self
    0.72
     foothold
    0.72
    Act Density 0.058%

    No Known Activations