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
    them
    -0.19
    unately
    -0.17
    cul
    -0.15
    ise
    -0.15
    ly
    -0.15
    æģµ
    -0.15
    ucs
    -0.15
    orsi
    -0.15
    luž
    -0.15
    ekk
    -0.14
    POSITIVE LOGITS
    soever
    0.45
    /if
    0.44
    EVER
    0.33
     they
    0.31
     faced
    0.29
     we
    0.28
     asked
    0.28
    -либо
    0.28
    /how
    0.27
    ver
    0.26
    Act Density 0.136%

    No Known Activations