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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons and contrasts

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

    followed by "another" or "other"

    np_acts-logits-general · gemini-2.0-flash

    one ... another/other/any

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.55
     चीज़ों
    -0.46
     lenker
    -0.43
    期刊论文
    -0.43
    LookAnd
    -0.42
     muligt
    -0.42
    Ivo
    -0.41
    懸
    -0.41
    éens
    -0.41
     #
    -0.41
    POSITIVE LOGITS
    extAlignment
    0.78
    AxisAlignment
    0.76
    ImageContext
    0.70
    Geplaatst
    0.66
    GHIJKLM
    0.65
    RectangleBorder
    0.61
    SequentialGroup
    0.61
     تانيه
    0.61
    клопе
    0.60
    Климат
    0.58
    Act Density 0.102%

    No Known Activations