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

    Neuronpedia

    INDEX
    Explanations

    specific patterns and symbols that may relate to formatting or structure in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     or
    -0.65
     #
    -0.56
     A
    -0.55
     L
    -0.54
     man
    -0.54
     OR
    -0.53
     ـ
    -0.52
     •
    -0.52
     ·
    -0.51
     at
    -0.51
    POSITIVE LOGITS
     pleaſure
    1.22
     Majefty
    1.22
     ſtate
    1.21
     ſche
    1.18
     purpoſe
    1.17
     Jefus
    1.14
    ſelves
    1.10
     ſever
    1.10
     Shakspeare
    1.10
     itſelf
    1.09
    Act Density 1.618%

    No Known Activations