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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by underscores or whitespace

    np_acts-logits-general · gemini-2.0-flash

    formatting separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كومونز
    -0.83
    !*\
    -0.82
     Linus
    -0.78
     estimés
    -0.73
    ệc
    -0.73
     BoxFit
    -0.72
    Morfologia
    -0.71
     nią
    -0.70
    toHaveBeen
    -0.70
    ">—
    -0.70
    POSITIVE LOGITS
    ................
    1.16
    ________________
    0.90
    ----------------
    0.82
    ################
    0.81
                                   
    0.75
    ================
    0.69
    ../../
    0.69
    …………………………………………
    0.66
    ………………………………
    0.65
                           
    0.64
    Act Density 0.491%

    No Known Activations