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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥ
    -0.16
     Cue
    -0.16
     Webb
    -0.15
     Cron
    -0.15
    ummer
    -0.14
    arian
    -0.14
    vid
    -0.14
    ennie
    -0.14
     Builder
    -0.13
    -
    -0.13
    POSITIVE LOGITS
    whose
    0.17
    edException
    0.17
    ĸ
    0.16
    SystemService
    0.16
     whose
    0.16
    afone
    0.16
    which
    0.15
     а
    0.15
    istra
    0.15
    é½
    0.15
    Act Density 0.043%

    No Known Activations