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

    Neuronpedia

    INDEX
    Explanations

    names of people (e.g., Elijah, Franz, Erin)

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynt
    -0.97
    ynthesis
    -0.94
    nik
    -0.93
    onic
    -0.89
    nar
    -0.83
    ento
    -0.83
    metry
    -0.82
    yg
    -0.82
    metic
    -0.82
    anic
    -0.80
    POSITIVE LOGITS
     Timber
    0.75
    wind
    0.75
     Carib
    0.72
    ACTED
    0.72
     Crossing
    0.71
     Flames
    0.70
     Burnett
    0.68
     Cullen
    0.66
    raft
    0.66
    naires
    0.66
    Act Density 0.040%

    No Known Activations