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

    Neuronpedia

    INDEX
    Explanations

    various instances of the letter 's' in differing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.62
     pleaſure
    -1.56
     purpoſe
    -1.55
     itſelf
    -1.54
     ―――――
    -1.51
     raiſ
    -1.45
     fubject
    -1.44
    NUMX
    -1.43
     Anſ
    -1.41
     faſt
    -1.39
    POSITIVE LOGITS
    s
    1.34
     his
    1.27
     His
    1.03
     
    1.02
     my
    0.98
    his
    0.98
    His
    0.93
     Her
    0.92
     (
    0.92
     I
    0.91
    Act Density 0.206%

    No Known Activations