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

    Neuronpedia

    INDEX
    Explanations

    phrases related to distinct or unique sets of items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to different sets of criteria or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.77
    Fight
    -0.74
    ï¸ı
    -0.70
    BLE
    -0.69
    loo
    -0.67
     Souls
    -0.66
    perse
    -0.65
    ãĥĨãĤ£
    -0.65
    IBLE
    -0.64
     Taste
    -0.63
    POSITIVE LOGITS
    offs
    1.12
    tle
    0.99
    list
    0.87
    ter
    0.84
    eq
    0.83
    ters
    0.81
    off
    0.81
    meal
    0.80
    limits
    0.79
    tering
    0.78
    Act Density 0.031%

    No Known Activations