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

    Neuronpedia

    INDEX
    Explanations

    data sources and performance metrics related to online content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.18
    1:0.03
    2:0.03
    3:0.06
    4:0.08
    5:0.12
    6:0.07
    7:0.03
    8:0.18
    9:0.11
    10:0.01
    11:0.04
    Negative Logits
     hail
    -1.78
     brackets
    -1.66
     helic
    -1.65
     flyers
    -1.62
    ifax
    -1.56
     Canaver
    -1.52
     billed
    -1.50
     trolls
    -1.48
     transsexual
    -1.47
     Lazarus
    -1.45
    POSITIVE LOGITS
    mA
    1.90
    dB
    1.71
    Boo
    1.71
    kw
    1.65
    umption
    1.64
    Enable
    1.60
    ight
    1.57
    Huh
    1.57
    �
    1.56
    UI
    1.56
    Act Density 0.001%

    No Known Activations