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

    Neuronpedia

    INDEX
    Explanations

    dates in the format "Month Day" or just the month

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Mon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Norn
    -0.89
    ACTED
    -0.78
    NRS
    -0.68
    rating
    -0.67
    LESS
    -0.67
    REE
    -0.67
    ENG
    -0.65
    avorite
    -0.65
    lessly
    -0.65
    atory
    -0.64
    POSITIVE LOGITS
    roe
    1.07
    ths
    1.03
    strous
    0.96
    ument
    0.95
    etheless
    0.90
    STER
    0.83
    cipled
    0.83
    itored
    0.82
    icol
    0.82
    cture
    0.80
    Act Density 0.016%

    No Known Activations