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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate correctness or suitability in context

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

    correct or appropriate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VIAF
    -0.41
     VIAF
    -0.39
     ddelweddau
    -0.38
    stylers
    -0.38
    龇
    -0.38
    timeFormat
    -0.37
    フィン
    -0.36
    YourGuide
    -0.35
     Banca
    -0.35
    /*++
    -0.35
    POSITIVE LOGITS
    Correct
    0.69
    Appropriate
    0.68
    correct
    0.68
     correct
    0.67
    appropriate
    0.65
     Correct
    0.65
     Appropriate
    0.64
     appropriate
    0.63
     correctly
    0.62
     CORRECT
    0.60
    Act Density 0.036%

    No Known Activations