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

    Neuronpedia

    INDEX
    Explanations

    dates in the format "Nov [day]"

    oai_token-act-pair · gpt-3.5-turbo

    dates mentioned in the context of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jriwal
    -0.89
    Reviewer
    -0.83
    edIn
    -0.76
    ngth
    -0.68
     Kush
    -0.67
     fore
    -0.64
     gifted
    -0.64
    holding
    -0.63
    adder
    -0.63
    irlf
    -0.63
    POSITIVE LOGITS
    isco
    1.00
    uary
    0.92
    ice
    0.88
    omore
    0.86
    ices
    0.86
    iors
    0.81
    rome
    0.79
    ionics
    0.79
    imal
    0.78
    onna
    0.77
    Act Density 0.007%

    No Known Activations