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

    Neuronpedia

    INDEX
    Explanations

    words related to people's names, particularly surnames

    oai_token-act-pair · gpt-3.5-turbo

    words related to people's names or surnames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Galileo
    -0.72
     Croatian
    -0.67
     Worlds
    -0.65
     Baal
    -0.63
     gradient
    -0.63
     [|
    -0.61
     Pastebin
    -0.60
     Eleven
    -0.59
    ibrary
    -0.59
     Metatron
    -0.59
    POSITIVE LOGITS
    issance
    0.82
    ney
    0.82
    lish
    0.82
    zie
    0.79
    aghan
    0.78
    igan
    0.76
    agall
    0.76
    SHA
    0.75
    ulty
    0.75
    ynski
    0.73
    Act Density 0.071%

    No Known Activations