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

    Neuronpedia

    INDEX
    Explanations

    names related to Italian heritage

    oai_token-act-pair · gpt-3.5-turbo

    words and suffix patterns related to names or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spin
    -0.83
    rill
    -0.76
    phe
    -0.73
    liest
    -0.72
    \\\\\\\\
    -0.72
    rified
    -0.70
    ãĤ°
    -0.70
    Ü
    -0.69
    ãĥª
    -0.69
    pir
    -0.69
    POSITIVE LOGITS
    zzi
    1.18
    Äĩ
    1.18
    otti
    1.14
    ère
    1.05
    zzo
    1.05
    ucci
    1.01
    ennes
    0.97
    orno
    0.96
    arella
    0.95
    zzle
    0.93
    Act Density 0.088%

    No Known Activations