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

    Neuronpedia

    INDEX
    Explanations

    data metrics and statistical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.04
    2:0.02
    3:0.08
    4:0.31
    5:0.03
    6:0.04
    7:0.05
    8:0.09
    9:0.06
    10:0.04
    11:0.06
    Negative Logits
    DragonMagazine
    -2.12
    artifacts
    -1.89
    nets
    -1.89
    someone
    -1.89
    contract
    -1.81
    inner
    -1.81
    stocks
    -1.79
    tl
    -1.78
    arson
    -1.77
    heid
    -1.76
    POSITIVE LOGITS
     respectively
    5.30
     apiece
    2.43
     alike
    2.31
     respective
    2.23
     Calder
    2.13
    +,
    2.01
     Bern
    1.81
    apan
    1.79
     default
    1.76
     Cinema
    1.75
    Act Density 0.052%

    No Known Activations