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

    Neuronpedia

    INDEX
    Explanations

    references to specific months

    oai_token-act-pair · gpt-3.5-turbo

    references to specific months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emort
    -0.81
    anooga
    -0.77
     behavi
    -0.71
    ioch
    -0.71
    otle
    -0.67
    inburgh
    -0.66
    querque
    -0.64
     Errors
    -0.63
    utf
    -0.63
    jri
    -0.63
    POSITIVE LOGITS
    flower
    0.90
    iversary
    0.88
    days
    0.83
    ipolar
    0.78
    ths
    0.76
     Ples
    0.72
    ruary
    0.72
    nard
    0.71
    uary
    0.70
    fair
    0.70
    Act Density 0.038%

    No Known Activations