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

    Neuronpedia

    INDEX
    Explanations

    instances of errors or oversights in a text

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

    mistakes, errors, and accidents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.36
    criminator
    -0.34
    🇶
    -0.34
    abon
    -0.34
    GN
    -0.33
    vars
    -0.33
    Médaille
    -0.32
     posse
    -0.31
     ffilmiau
    -0.31
    提
    -0.31
    POSITIVE LOGITS
     mistake
    0.70
    忘記
    0.68
     forgot
    0.66
    忘记
    0.65
     mistakes
    0.64
     accidentally
    0.64
     mistakenly
    0.63
     виправивши
    0.63
     Mistakes
    0.61
     Mistake
    0.61
    Act Density 0.466%

    No Known Activations