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

    Neuronpedia

    INDEX
    Explanations

    words related to official titles or positions

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of "ial" suffixes, indicating a focus on adjectives or concepts associated with some characteristic or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.90
    EEK
    -0.89
    ãĥ¯ãĥ³
    -0.85
    Ò
    -0.81
    rir
    -0.81
    URA
    -0.77
    herty
    -0.77
    ATHER
    -0.74
    CHA
    -0.73
    urai
    -0.72
    POSITIVE LOGITS
    ysis
    1.16
    ity
    1.08
    ogue
    1.01
    ities
    0.88
    ogy
    0.84
    arial
    0.80
    ized
    0.78
    tarians
    0.77
    acies
    0.76
    abolic
    0.75
    Act Density 0.019%

    No Known Activations