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

    Neuronpedia

    INDEX
    Explanations

    variations of punctuation and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.55
    ,
    -0.49
     to
    -0.44
     (
    -0.42
     
    -0.42
     có
    -0.41
    ...
    -0.39
     so
    -0.39
    <eos>
    -0.38
    /
    -0.38
    POSITIVE LOGITS
     myſelf
    1.51
     itſelf
    1.44
     Theſe
    1.41
     Majefty
    1.41
     Jefus
    1.39
     Efq
    1.38
     purpoſe
    1.36
     themſelves
    1.35
     pleaſure
    1.34
     poffible
    1.34
    Act Density 0.872%

    No Known Activations