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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.12
    3:0.06
    4:0.06
    5:0.03
    6:0.06
    7:0.19
    8:0.07
    9:0.06
    10:0.08
    11:0.16
    Negative Logits
    geries
    -1.84
    flo
    -1.60
    holder
    -1.53
    omination
    -1.50
    arson
    -1.45
    plates
    -1.44
    jab
    -1.44
    ocr
    -1.43
    porter
    -1.40
    faces
    -1.38
    POSITIVE LOGITS
    ISION
    1.55
     Subtle
    1.46
     Nun
    1.43
     Emir
    1.42
     Goth
    1.41
     msec
    1.40
     Mask
    1.39
     Muse
    1.38
    beit
    1.38
    ========
    1.37
    Act Density 0.002%

    No Known Activations