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

    Neuronpedia

    INDEX
    Explanations

    instances of formatting or special characters that create visual separators or structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ////////////////
    -0.75
    ................
    -0.65
    ________________
    -0.65
    …………………………………………
    -0.62
    ================
    -0.61
    ----------------
    -0.59
    ::::::::::::::::
    -0.57
    ################
    -0.55
    ————————————————
    -0.55
    ****************
    -0.53
    POSITIVE LOGITS
    MessageOf
    0.59
    :✨
    0.54
     @"/
    0.53
     myſelf
    0.51
    pgterms
    0.46
    Sucesor
    0.46
     ſche
    0.45
     propOrder
    0.45
     ========
    0.45
     Houſe
    0.45
    Act Density 0.775%

    No Known Activations