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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns and interrogative words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Baton
    -0.70
    ed
    -0.67
     relationship
    -0.63
     Dampf
    -0.63
     Tief
    -0.62
    Aly
    -0.61
     Folsom
    -0.61
    Peek
    -0.60
    rüstung
    -0.59
    tony
    -0.59
    POSITIVE LOGITS
     WHICH
    1.85
     which
    1.77
    which
    1.71
     Which
    1.64
    Which
    1.58
     wich
    1.41
    Datuak
    1.32
    hich
    1.25
    ซึ่ง
    1.09
     welches
    1.04
    Act Density 0.232%

    No Known Activations