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

    Neuronpedia

    INDEX
    Explanations

    the word "which" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucker
    -0.18
    taire
    -0.17
    argin
    -0.16
    ÎŃÏģα
    -0.15
    gres
    -0.15
    aws
    -0.14
    edla
    -0.14
    evice
    -0.14
    illis
    -0.14
    mas
    -0.14
    POSITIVE LOGITS
    wart
    0.16
    aná
    0.15
     gard
    0.15
    lich
    0.15
    _unregister
    0.15
    bedo
    0.15
     defaultManager
    0.14
    رش
    0.14
    ongyang
    0.14
    andbox
    0.13
    Act Density 0.098%

    No Known Activations