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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals, such as names and titles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and titles of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.92
    comed
    -0.76
    20439
    -0.76
    oooooooo
    -0.73
    atform
    -0.72
    abouts
    -0.71
    ËĪ
    -0.71
    obyl
    -0.71
    */(
    -0.70
    flies
    -0.69
    POSITIVE LOGITS
     Hyde
    0.91
     Ana
    0.86
     Irwin
    0.85
     Solomon
    0.83
     Hu
    0.83
     Ellison
    0.82
     Fernandez
    0.82
     Ba
    0.81
     Fla
    0.80
     Cout
    0.80
    Act Density 0.095%

    No Known Activations