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

    Neuronpedia

    INDEX
    Explanations

    instances of partial phrases and comparisons

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

    almost or nearly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.58
    ValueGenerated
    -0.49
     Tara
    -0.49
    idum
    -0.46
    yant
    -0.44
    ioc
    -0.42
    kuuta
    -0.42
     chi̍t
    -0.42
     thoroughly
    -0.41
     Hän
    -0.41
    POSITIVE LOGITS
    Almost
    0.75
     Almost
    0.67
    almost
    0.60
    Casi
    0.54
     almost
    0.54
    ientôt
    0.50
    Nearly
    0.49
     presque
    0.48
     Nearly
    0.47
     aproape
    0.47
    Act Density 0.013%

    No Known Activations