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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umpy
    -0.15
    reve
    -0.15
    ENDER
    -0.14
     Bil
    -0.14
    ä¹³
    -0.14
    orsche
    -0.14
    à¹Ĥà¸ŀ
    -0.14
     wi
    -0.13
    è¼Ŀ
    -0.13
    ữ
    -0.13
    POSITIVE LOGITS
    ogne
    0.16
    /Peak
    0.16
    adeon
    0.16
     Christoph
    0.16
     McGr
    0.14
    akit
    0.14
    agma
    0.14
    itag
    0.14
    WK
    0.14
    ond
    0.14
    Act Density 0.004%

    No Known Activations