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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.07
    3:0.10
    4:0.07
    5:0.09
    6:0.07
    7:0.08
    8:0.08
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
    brow
    -1.74
    igmatic
    -1.68
    abeth
    -1.67
    loo
    -1.65
    alone
    -1.63
     licens
    -1.63
    edin
    -1.60
    fax
    -1.59
    aler
    -1.57
    olin
    -1.54
    POSITIVE LOGITS
     overturned
    1.75
     raping
    1.61
     Cheong
    1.59
    itism
    1.54
     blaming
    1.54
    「
    1.54
    Timeout
    1.52
     unaccount
    1.50
     pressuring
    1.50
     overturn
    1.46
    Act Density 0.000%

    No Known Activations