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

    Neuronpedia

    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isable
    -0.72
     bats
    -0.67
    elaide
    -0.66
    ugu
    -0.65
     rusty
    -0.64
     signatures
    -0.63
     warrant
    -0.61
    ovember
    -0.60
     wiser
    -0.60
    itially
    -0.60
    POSITIVE LOGITS
    ij士
    0.94
    downs
    0.77
     Friedman
    0.76
    ·
    0.75
    itar
    0.72
    Į
    0.72
    glers
    0.71
    ¼
    0.70
    zinski
    0.70
    stakes
    0.69
    Act Density 0.070%

    No Known Activations