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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bezeichneter
    -1.67
     Efq
    -1.64
     myſelf
    -1.60
    Personendaten
    -1.59
     pleaſure
    -1.59
     faſt
    -1.58
     ſever
    -1.57
     ſind
    -1.56
    ſelf
    -1.56
     ―――――
    -1.55
    POSITIVE LOGITS
    ,
    1.29
    .
    1.21
     
    1.10
     (
    0.97
    ↵↵
    0.96
    -
    0.91
    /
    0.91
     to
    0.90
     -
    0.88
    (
    0.88
    Act Density 6.164%

    No Known Activations