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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and charges

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "day" and variations related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hered
    -0.77
    ittees
    -0.66
    adem
    -0.64
    itia
    -0.64
    requ
    -0.63
     Scha
    -0.63
     Luxem
    -0.62
     Notting
    -0.62
    ãĥª
    -0.61
    arium
    -0.61
    POSITIVE LOGITS
    AY
    1.21
    DAY
    1.09
    OUT
    1.06
    WARD
    0.93
    ER
    0.93
    CAST
    0.93
    ARY
    0.91
    LY
    0.90
    NESS
    0.89
    RY
    0.88
    Act Density 0.006%

    No Known Activations