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

    Neuronpedia

    INDEX
    Explanations

    examples that illustrate a point or concept

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "for example."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ral
    -0.73
    orate
    -0.72
    elled
    -0.70
    inated
    -0.69
    sil
    -0.69
    inates
    -0.69
    ormal
    -0.69
    lled
    -0.68
    ELY
    -0.67
    dr
    -0.66
    POSITIVE LOGITS
     subp
    0.69
     Schn
    0.66
     Stri
    0.66
     Chomsky
    0.66
    wcsstore
    0.64
    xon
    0.63
    =#
    0.63
     suppose
    0.62
     Fowler
    0.62
    herty
    0.61
    Act Density 0.026%

    No Known Activations