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

    Neuronpedia

    INDEX
    Explanations

    Java annotations related to testing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hol
    -0.17
    ismet
    -0.15
    asse
    -0.15
    ubl
    -0.15
    éijij
    -0.15
    itten
    -0.15
    pid
    -0.15
     van
    -0.14
     Hol
    -0.14
    emie
    -0.14
    POSITIVE LOGITS
    597
    0.17
    avid
    0.16
    amed
    0.15
    (Collision
    0.15
    egie
    0.15
    meni
    0.15
     stump
    0.14
    :variables
    0.14
    -thumbnails
    0.14
     smo
    0.14
    Act Density 0.005%

    No Known Activations