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

    Neuronpedia

    INDEX
    Explanations

    adverbs that express frequency or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that indicate frequency or typical behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pron
    -0.73
    athered
    -0.72
    ËĪ
    -0.68
    arthy
    -0.64
    "},"
    -0.64
    adr
    -0.64
    umbn
    -0.63
    spl
    -0.62
    âĹ¼
    -0.61
    him
    -0.61
    POSITIVE LOGITS
    adays
    0.82
     Ago
    0.81
    terday
    0.78
    terness
    0.71
    theless
    0.71
     Helpful
    0.70
    nown
    0.69
     Comes
    0.69
    etheless
    0.68
     Ones
    0.67
    Act Density 0.094%

    No Known Activations