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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "for" and related phrases indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.66
    TintMode
    -0.64
     leçon
    -0.61
     grève
    -0.58
     Zuz
    -0.57
     DRS
    -0.57
    ớp
    -0.57
     PDI
    -0.56
    Retrieved
    -0.56
     faſt
    -0.55
    POSITIVE LOGITS
    Regarding
    0.87
     Regarding
    0.85
     Concerning
    0.77
     касается
    0.77
    Concerning
    0.75
     regarding
    0.73
    至于
    0.69
     بالنسبة
    0.66
     поводу
    0.64
    至於
    0.62
    Act Density 0.363%

    No Known Activations