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

    Neuronpedia

    INDEX
    Explanations

    instances of questioning personal or societal issues

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

    what's wrong with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.66
    SourceChecksum
    -0.60
     виправивши
    -0.56
    contentLoaded
    -0.56
    BeginContext
    -0.54
    Atsauces
    -0.53
     Qaraldi
    -0.53
    haikusbot
    -0.52
    IndentedString
    -0.52
    ごちそうさまでした
    -0.52
    POSITIVE LOGITS
    oreille
    0.41
    ItemBackground
    0.40
     wrong
    0.39
    wrong
    0.37
    me
    0.37
    wholesome
    0.37
    seater
    0.37
    shtml
    0.36
    className
    0.35
    Wrong
    0.35
    Act Density 0.008%

    No Known Activations