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

    Neuronpedia

    INDEX
    Explanations

    references to events or activities taking place at specific locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "take place."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.72
    edded
    -0.67
    rouse
    -0.65
    rc
    -0.65
    ooks
    -0.65
    incinn
    -0.64
    illard
    -0.64
    cest
    -0.64
    idth
    -0.63
    oneliness
    -0.63
    POSITIVE LOGITS
    Ú
    0.86
    Ò
    0.85
    ÑĮ
    0.77
    ãĤ¯
    0.77
    ãĥĥãĤ¯
    0.77
    VK
    0.75
    Ö
    0.74
    bos
    0.73
    ãĤ¦
    0.72
    Parameter
    0.71
    Act Density 0.022%

    No Known Activations