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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that signify the end of a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.05
    2:0.08
    3:0.08
    4:0.10
    5:0.07
    6:0.09
    7:0.08
    8:0.07
    9:0.06
    10:0.09
    11:0.09
    Negative Logits
    lihood
    -1.60
    tesque
    -1.53
     whiff
    -1.44
    ements
    -1.42
    ——
    -1.41
    espie
    -1.41
    Vill
    -1.38
    levision
    -1.38
     (@
    -1.38
    Media
    -1.35
    POSITIVE LOGITS
     Canaver
    1.64
     conduc
    1.63
     Berk
    1.56
    anu
    1.56
     dues
    1.55
     indo
    1.55
    onse
    1.53
    yang
    1.45
     warr
    1.44
     Aki
    1.43
    Act Density 0.000%

    No Known Activations