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

    Neuronpedia

    INDEX
    Explanations

    pattern-like structures or sequences in numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.73
     fifteenth
    -0.63
    IsContent
    -0.60
     disambiguazione
    -0.60
    oredCriteria
    -0.59
     Fourteen
    -0.54
     fourteen
    -0.51
     seventeen
    -0.51
    bootstrapcdn
    -0.49
    EDEFAULT
    -0.48
    POSITIVE LOGITS
    6
    2.22
     Six
    1.92
     six
    1.88
     Sixth
    1.68
     SIX
    1.68
     sixth
    1.65
    六
    1.62
    Six
    1.60
    six
    1.59
    ６
    1.54
    Act Density 2.979%

    No Known Activations