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

    Neuronpedia

    INDEX
    Explanations

    proper nouns representing notable figures or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals who are notable or significant in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.63
    asions
    -0.60
     equival
    -0.60
    ooks
    -0.58
     VIDEOS
    -0.57
    given
    -0.57
    icans
    -0.55
    cats
    -0.55
    ulence
    -0.55
     tablets
    -0.54
    POSITIVE LOGITS
     hundred
    0.82
    Drive
    0.75
    esan
    0.75
     Hundred
    0.74
     beneficiary
    0.73
    handedly
    0.70
    uther
    0.67
     heartbeat
    0.67
     of
    0.67
     month
    0.66
    Act Density 0.058%

    No Known Activations