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

    Neuronpedia

    INDEX
    Explanations

    punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.08
    3:0.05
    4:0.08
    5:0.08
    6:0.08
    7:0.09
    8:0.08
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    VIDIA
    -1.69
     Superman
    -1.64
    umbledore
    -1.59
     Cipher
    -1.59
    Flash
    -1.54
     Codec
    -1.52
     Canter
    -1.52
     Bahá
    -1.48
     signalling
    -1.48
    speaking
    -1.46
    POSITIVE LOGITS
    ebted
    1.93
    ンジ
    1.80
     backbone
    1.78
    seless
    1.78
    INESS
    1.77
     sorely
    1.71
    verages
    1.70
    benef
    1.64
    iets
    1.60
     accordingly
    1.56
    Act Density 0.000%

    No Known Activations