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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and terms related to historical or political figures, specifically focusing on the name "Iri"

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific individuals or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spin
    -0.82
    egg
    -0.82
    size
    -0.79
    bags
    -0.76
    ablishment
    -0.70
    meal
    -0.69
    correct
    -0.68
    fighters
    -0.65
    coat
    -0.64
    rex
    -0.64
    POSITIVE LOGITS
    yah
    1.03
    ya
    1.01
    uddy
    0.87
    Äĩ
    0.83
    OUS
    0.80
    oux
    0.80
    vana
    0.80
    olla
    0.78
    opsis
    0.78
    YA
    0.77
    Act Density 0.023%

    No Known Activations