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

    Neuronpedia

    INDEX
    Explanations

    words related to sets or collections

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "set" and its related plurals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.76
    Fight
    -0.73
    ï¸ı
    -0.73
    IBLE
    -0.69
    Sense
    -0.68
     Souls
    -0.68
    perse
    -0.65
    æĺ¯
    -0.65
    ãĥĨãĤ£
    -0.64
    Strength
    -0.62
    POSITIVE LOGITS
    offs
    1.10
    tle
    0.95
    list
    0.85
    meal
    0.85
    off
    0.82
    eq
    0.82
    atum
    0.79
    table
    0.78
    ters
    0.78
    mate
    0.78
    Act Density 0.030%

    No Known Activations