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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of month/day in various documents

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values associated with dates and timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atis
    -0.89
    atics
    -0.87
    abwe
    -0.81
    ramid
    -0.81
    atic
    -0.76
    akens
    -0.74
    akespe
    -0.72
    rats
    -0.72
    anned
    -0.72
    akening
    -0.71
    POSITIVE LOGITS
    st
    0.84
    ¯¯
    0.76
    vier
    0.74
    rd
    0.73
    ¯¯¯¯
    0.72
    00
    0.67
     msec
    0.67
    backer
    0.66
    803
    0.66
    manship
    0.65
    Act Density 0.044%

    No Known Activations