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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTWARE
    -0.79
    fill
    -0.68
    REDACTED
    -0.66
    Pac
    -0.66
    Iterator
    -0.65
    Russ
    -0.65
    glass
    -0.64
    ships
    -0.63
    cro
    -0.63
    HTTP
    -0.63
    POSITIVE LOGITS
     least
    1.23
    onement
    1.00
    abase
    0.93
     halftime
    0.88
    rial
    0.87
     times
    0.86
    roph
    0.84
     home
    0.82
    yp
    0.82
     stake
    0.80
    Act Density 0.243%

    No Known Activations