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

    Neuronpedia

    INDEX
    Explanations

    negations or terms indicating a lack of applicability or suitability

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

    not followed by positive quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unofficial
    -0.42
     gotta
    -0.39
     prohibido
    -0.39
     butuh
    -0.37
    official
    -0.36
     fallu
    -0.36
    Incomplete
    -0.35
    MOST
    -0.35
     ESPEC
    -0.35
     ESPECIAL
    -0.34
    POSITIVE LOGITS
     satisfactory
    0.71
     satisfactorily
    0.65
     simple
    0.62
     straightforward
    0.62
    TagMode
    0.59
     adequately
    0.58
     trivial
    0.57
     simply
    0.57
     solely
    0.54
     zufried
    0.53
    Act Density 0.304%

    No Known Activations