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

    Neuronpedia

    INDEX
    Explanations

    quoted phrases or direct quotes from the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.08
    3:0.06
    4:0.08
    5:0.08
    6:0.08
    7:0.07
    8:0.09
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    raf
    -2.98
    )\
    -2.87
     \"
    -2.86
    ](
    -2.83
    р
    -2.80
     «
    -2.72
     �
    -2.71
    orph
    -2.65
    ,)
    -2.61
    н
    -2.59
    POSITIVE LOGITS
     MacArthur
    2.83
     certs
    2.54
     pastry
    2.46
     Honolulu
    2.45
    stanbul
    2.45
    utsche
    2.40
     Nanto
    2.39
     examiner
    2.38
     TSA
    2.37
     Tillerson
    2.30
    Act Density 0.000%

    No Known Activations