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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repetition or reference to time-related contexts

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

    again or just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kesehatan
    -0.44
    følge
    -0.44
     nég
    -0.42
    Vía
    -0.40
     коррек
    -0.39
    gæ
    -0.39
    onPause
    -0.38
     inderdaad
    -0.38
    低い
    -0.38
    impulan
    -0.38
    POSITIVE LOGITS
    又
    2.11
     又
    1.73
    他又
    1.41
    我又
    1.30
    又有
    1.29
    又在
    1.14
    又不
    1.11
    又被
    1.11
    又要
    1.08
    又能
    1.06
    Act Density 0.001%

    No Known Activations