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

    Neuronpedia

    INDEX
    Explanations

    numbers represented as decimal fractions

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly in the form of measurements or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemImage
    -0.80
    lehem
    -0.73
    cerning
    -0.64
    organic
    -0.64
    liga
    -0.63
    ercise
    -0.63
    creen
    -0.62
     conduc
    -0.62
    krit
    -0.62
    ervative
    -0.61
    POSITIVE LOGITS
    xff
    1.11
    xe
    0.93
    x
    0.92
    xd
    0.91
     0
    0.84
    xb
    0.82
    xc
    0.81
    644
    0.78
    xa
    0.75
    MQ
    0.74
    Act Density 0.024%

    No Known Activations