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

    Neuronpedia

    INDEX
    Explanations

    frequent mentions of the word "that" and related high-activation content within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ«ãĤ¯
    -0.14
    ossible
    -0.14
    .ParseException
    -0.14
    835
    -0.14
     Already
    -0.13
    834
    -0.13
    pegawai
    -0.13
    827
    -0.13
    895
    -0.13
    avanaugh
    -0.13
    POSITIVE LOGITS
     recently
    0.20
     recent
    0.19
     lately
    0.17
     soon
    0.17
     always
    0.16
    ish
    0.16
    always
    0.15
     subject
    0.15
     forthcoming
    0.15
     upcoming
    0.14
    Act Density 0.005%

    No Known Activations