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

    Neuronpedia

    INDEX
    Explanations

    numbers and statistics related to scores or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.05
    3:0.17
    4:0.09
    5:0.06
    6:0.06
    7:0.10
    8:0.07
    9:0.05
    10:0.06
    11:0.10
    Negative Logits
    orthodox
    -2.69
     isol
    -2.63
    thodox
    -2.39
     isolate
    -2.36
    orno
    -2.23
    infeld
    -2.19
    informed
    -2.17
     supplemented
    -2.14
     anch
    -2.12
    igslist
    -2.10
    POSITIVE LOGITS
     0
    3.79
     2
    3.63
     1
    3.46
     3
    3.28
     4
    2.96
     Tot
    2.83
     5
    2.73
     TOTAL
    2.62
     tf
    2.59
     6
    2.59
    Act Density 0.005%

    No Known Activations