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

    Neuronpedia

    INDEX
    Explanations

    words with the "rep" or "repeated" pattern in them

    oai_token-act-pair · gpt-3.5-turbo

    the term "rep" and its variations, indicating a focus on references to a representative or representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gaard
    -0.77
     Galile
    -0.68
    ahime
    -0.67
     Aval
    -0.67
    scape
    -0.66
    footed
    -0.64
    istically
    -0.64
     Archdemon
    -0.64
     à¨
    -0.63
    liners
    -0.63
    POSITIVE LOGITS
    ublic
    1.42
    atri
    1.24
    orters
    1.14
    resents
    1.13
    rint
    1.10
    arations
    0.99
    utations
    0.99
    rep
    0.97
    utation
    0.97
    onse
    0.95
    Act Density 0.011%

    No Known Activations