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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "highlight" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñģли
    -0.17
    zzle
    -0.16
    ponder
    -0.15
    zw
    -0.15
    nd
    -0.14
    scape
    -0.14
    jon
    -0.14
    алеж
    -0.14
    urence
    -0.14
    load
    -0.14
    POSITIVE LOGITS
    enment
    0.19
    ened
    0.18
    ting
    0.17
    nings
    0.17
     reels
    0.16
    ening
    0.16
     reel
    0.16
    onse
    0.15
    uates
    0.15
    QRS
    0.15
    Act Density 0.022%

    No Known Activations