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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly focusing on names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dylib
    -0.88
    ModLoader
    -0.77
    ascript
    -0.70
     Haitian
    -0.70
     Betty
    -0.68
     Pixie
    -0.68
     Colombian
    -0.67
     Mae
    -0.66
     Algeria
    -0.64
     Nicarag
    -0.63
    POSITIVE LOGITS
    acca
    0.83
    ibl
    0.81
    aghan
    0.74
    kov
    0.72
    ansky
    0.71
    lez
    0.71
    essen
    0.70
    gall
    0.69
    ovy
    0.68
    iot
    0.68
    Act Density 0.220%

    No Known Activations