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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numeric values related to measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.72
    ItemImage
    -0.70
     conduc
    -0.67
    ercise
    -0.66
    creen
    -0.64
     multiplying
    -0.61
    £ı
    -0.59
    cerning
    -0.58
    Lago
    -0.58
    Ü
    -0.57
    POSITIVE LOGITS
    xff
    1.18
    xd
    0.93
    xe
    0.93
    xc
    0.87
    x
    0.87
    xa
    0.86
    xb
    0.85
    603
    0.82
    usc
    0.79
    uer
    0.79
    Act Density 0.031%

    No Known Activations