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

    Neuronpedia

    INDEX
    Explanations

    references to a specific department or institution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.04
    2:0.14
    3:0.10
    4:0.02
    5:0.02
    6:0.06
    7:0.11
    8:0.13
    9:0.08
    10:0.13
    11:0.08
    Negative Logits
    monton
    -1.33
    anooga
    -1.20
    amas
    -1.17
    astrous
    -1.17
    wrong
    -1.15
    sectional
    -1.14
    iev
    -1.10
    acky
    -1.06
    cedented
    -1.04
    roversial
    -1.04
    POSITIVE LOGITS
     Atkinson
    1.11
     Query
    1.10
     SMS
    0.99
     Salam
    0.99
     Fell
    0.95
     Aff
    0.95
     Beetle
    0.95
     MAP
    0.92
     ENG
    0.92
     Alv
    0.91
    Act Density 0.196%

    No Known Activations