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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emphasis or surprise

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arte
    -0.82
    MSN
    -0.69
    utterstock
    -0.68
    ãĤ±
    -0.67
    verbs
    -0.66
    ĺħ
    -0.65
    indal
    -0.64
    pex
    -0.63
     ®
    -0.63
    BILITIES
    -0.63
    POSITIVE LOGITS
    WHERE
    0.73
    TPS
    0.73
    there
    0.68
     gunshots
    0.63
    when
    0.62
    depending
    0.61
    rought
    0.60
     dement
    0.60
    fect
    0.59
    different
    0.59
    Act Density 0.231%

    No Known Activations