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

    Neuronpedia

    INDEX
    Explanations

    references to demographics and representation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aln
    -0.17
    aze
    -0.15
    γÏĩ
    -0.14
    νÏİ
    -0.14
    Ľå»º
    -0.14
    æ³
    -0.14
    rit
    -0.14
    asper
    -0.14
    ĶĦ
    -0.14
    apur
    -0.14
    POSITIVE LOGITS
     into
    0.36
     onto
    0.33
    into
    0.29
    onto
    0.27
     Into
    0.27
    Into
    0.24
     INTO
    0.23
     vÃło
    0.23
    _into
    0.20
    à¹Ģà¸Ĥ
    0.18
    Act Density 0.090%

    No Known Activations