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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iov
    -0.16
    edu
    -0.16
    ski
    -0.15
    sky
    -0.14
    iloc
    -0.14
    hound
    -0.14
    atory
    -0.14
     behalf
    -0.13
    cul
    -0.13
    sumer
    -0.13
    POSITIVE LOGITS
    lä
    0.17
    olley
    0.17
    APPER
    0.15
    celik
    0.15
    stal
    0.15
    etin
    0.14
    iaux
    0.14
    stk
    0.14
     autoplay
    0.14
    soever
    0.13
    Act Density 0.079%

    No Known Activations