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

    Neuronpedia

    INDEX
    Explanations

    timestamps or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olson
    -0.78
    phal
    -0.63
    ocene
    -0.63
    pherd
    -0.62
    eger
    -0.59
    ativity
    -0.58
     reluct
    -0.58
    sen
    -0.58
    picture
    -0.58
     exha
    -0.58
    POSITIVE LOGITS
    00
    0.92
    arth
    0.77
    -+
    0.72
    ors
    0.71
    inen
    0.69
    ulse
    0.69
    raction
    0.69
    OPLE
    0.67
    iversary
    0.65
    ectomy
    0.65
    Act Density 0.050%

    No Known Activations