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

    Neuronpedia

    INDEX
    Explanations

    repetitive references to the concept of "more."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĽ´å¤ļ
    -0.17
     otherwise
    -0.16
     دÛĮگر
    -0.16
     Otherwise
    -0.16
    Otherwise
    -0.15
    que
    -0.15
     anymore
    -0.15
    visor
    -0.14
    otherwise
    -0.14
     autres
    -0.14
    POSITIVE LOGITS
     than
    0.43
    -than
    0.36
     of
    0.34
    than
    0.30
    Than
    0.27
     importantly
    0.25
     Than
    0.25
    _than
    0.24
    tti
    0.23
     THAN
    0.23
    Act Density 0.096%

    No Known Activations