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

    Neuronpedia

    INDEX
    Explanations

    numbers in a specific format and context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 15 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOAD
    -0.78
    atis
    -0.73
    ei
    -0.68
    itsch
    -0.68
    hee
    -0.65
    gie
    -0.64
    quit
    -0.64
    itized
    -0.64
    ĸļ
    -0.62
    hid
    -0.62
    POSITIVE LOGITS
     minutes
    0.84
    th
    0.82
     ILCS
    0.81
     mins
    0.79
    ances
    0.79
    rament
    0.75
    liest
    0.75
     Yard
    0.75
    rd
    0.72
    555
    0.70
    Act Density 0.154%

    No Known Activations