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

    Neuronpedia

    INDEX
    Explanations

    words related to signing or signatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vsk
    -0.44
    sbericht
    -0.40
    deras
    -0.38
    auce
    -0.37
    ILITIES
    -0.36
    cam
    -0.35
    gono
    -0.35
    multer
    -0.35
    mgang
    -0.35
    ocha
    -0.35
    POSITIVE LOGITS
     Sign
    0.69
     sign
    0.57
     الحره
    0.55
    Sign
    0.54
    0.54
    atories
    0.53
    ificance
    0.53
     Drapeau
    0.52
    posts
    0.52
    署
    0.51
    Act Density 0.126%

    No Known Activations