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

    Neuronpedia

    INDEX
    Explanations

    instances of the character 'C' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.04
    2:0.04
    3:0.05
    4:0.05
    5:0.05
    6:0.10
    7:0.08
    8:0.03
    9:0.05
    10:0.01
    11:0.39
    Negative Logits
    xus
    -2.49
    etting
    -2.45
    Stretch
    -2.28
    grain
    -2.21
    essen
    -2.15
    …]
    -2.14
    minist
    -2.09
    TL
    -2.08
    anqu
    -2.05
    omsky
    -2.01
    POSITIVE LOGITS
     Irma
    2.52
     Ivan
    2.49
     Juan
    2.46
     Mikhail
    2.41
     Francois
    2.41
     Natasha
    2.38
     Barb
    2.38
     Gus
    2.36
     Pepe
    2.35
     Jeb
    2.34
    Act Density 0.017%

    No Known Activations