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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cstdio
    -0.67
    tagHelperRunner
    -0.58
    adal
    -0.56
     trúc
    -0.54
    "?>
    -0.54
    Verdana
    -0.53
     resourceCulture
    -0.52
    ьев
    -0.52
    фии
    -0.52
    quat
    -0.51
    POSITIVE LOGITS
     only
    4.44
    only
    3.70
    Only
    3.43
     Only
    3.35
     ONLY
    3.10
    ONLY
    3.09
     seulement
    2.70
     только
    2.63
     tylko
    2.46
     hanya
    2.39
    Act Density 0.100%

    No Known Activations