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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gow
    -0.15
    alem
    -0.14
    cken
    -0.14
    .@
    -0.14
    clamation
    -0.14
    olan
    -0.14
    mund
    -0.13
    ino
    -0.13
     Darkness
    -0.13
    uation
    -0.13
    POSITIVE LOGITS
    rase
    0.17
    upon
    0.15
    soever
    0.15
    930
    0.14
    plier
    0.14
    zes
    0.14
    yx
    0.14
    /pi
    0.14
    ebp
    0.13
    otti
    0.13
    Act Density 0.041%

    No Known Activations