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

    Neuronpedia

    INDEX
    Explanations

    variations of the letter "C" and related symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.05
    3:0.09
    4:0.08
    5:0.15
    6:0.07
    7:0.04
    8:0.10
    9:0.04
    10:0.04
    11:0.20
    Negative Logits
    ...]
    -3.00
    ...)
    -2.76
     Seah
    -2.73
     Mong
    -2.73
     chall
    -2.72
    tons
    -2.72
     Gent
    -2.63
     Tuls
    -2.63
     princ
    -2.61
     nutshell
    -2.58
    POSITIVE LOGITS
     ­
    4.89
    —-
    4.24
    </
    3.91
    <<
    3.77
    ♦
    3.76
    «
    3.68
    ­
    3.61
    »
    3.60
    ‑
    3.56
     �
    3.50
    Act Density 0.172%

    No Known Activations