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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to specific individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the names "Powell" and "Qatar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essor
    -0.82
    nect
    -0.73
    ving
    -0.72
    ¯¯
    -0.69
    MW
    -0.69
    ively
    -0.68
    ICES
    -0.67
    leon
    -0.66
     Liberties
    -0.66
    amaz
    -0.66
    POSITIVE LOGITS
    anut
    0.77
    ongyang
    0.76
     Powell
    0.71
    quote
    0.70
     Mills
    0.70
     Hilton
    0.65
    alm
    0.64
     Hut
    0.63
    eln
    0.63
    hett
    0.63
    Act Density 0.069%

    No Known Activations