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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.09
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     freel
    -2.85
    licks
    -2.83
    ookie
    -2.75
    izzle
    -2.74
    undo
    -2.67
    evil
    -2.63
     alley
    -2.58
     Choi
    -2.55
    ravis
    -2.52
    cffffcc
    -2.50
    POSITIVE LOGITS
     ECB
    3.33
     IEEE
    2.91
     strengthened
    2.78
     integrating
    2.64
     cryptography
    2.60
     MRI
    2.54
    trust
    2.54
     Alloy
    2.53
     Mathematics
    2.50
     NATO
    2.43
    Act Density 0.000%

    No Known Activations