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

    Neuronpedia

    INDEX
    Explanations

    repeated use of the word "just" in various contexts

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

    Precedes a negative or softening word

    np_acts-logits-general · gemini-2.0-flash

    just qualifying statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     also
    -0.88
     zelfs
    -0.85
     sogar
    -0.81
     only
    -0.76
     также
    -0.75
    also
    -0.73
     dopiero
    -0.73
     également
    -0.73
     jopa
    -0.72
     именно
    -0.71
    POSITIVE LOGITS
     plain
    0.84
    单纯
    0.77
    دانشنامهٔ
    0.70
     sayin
    0.67
    ClientSize
    0.67
     general
    0.64
    而已
    0.63
     FYI
    0.62
     saja
    0.61
     للاسماء
    0.60
    Act Density 0.167%

    No Known Activations