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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter "s" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.23
     myſelf
    -1.17
     Majefty
    -1.12
    ſelf
    -1.09
     Efq
    -1.09
     itſelf
    -1.09
     purpoſe
    -1.08
     ſtate
    -1.07
     poffe
    -1.07
     raiſ
    -1.03
    POSITIVE LOGITS
    Theres
    0.61
     the
    0.56
     a
    0.54
    theres
    0.53
     theres
    0.53
    有
    0.51
    u
    0.51
     Theres
    0.51
     (
    0.50
    at
    0.49
    Act Density 0.082%

    No Known Activations