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

    Neuronpedia

    INDEX
    Explanations

    commas and other punctuation indicating separate clauses or items in a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.14
    3:0.06
    4:0.07
    5:0.03
    6:0.07
    7:0.17
    8:0.07
    9:0.02
    10:0.12
    11:0.17
    Negative Logits
    ombat
    -1.68
    ��
    -1.60
     Gleaming
    -1.58
    urbed
    -1.55
    culosis
    -1.52
    undown
    -1.50
    itionally
    -1.50
    ibly
    -1.48
    oak
    -1.47
    anwhile
    -1.45
    POSITIVE LOGITS
     Winc
    1.42
     Cumm
    1.39
     collaborator
    1.35
     mates
    1.31
     rivals
    1.30
     publishers
    1.25
    RAW
    1.24
     sibling
    1.24
     param
    1.23
     Grind
    1.22
    Act Density 0.057%

    No Known Activations