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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format "March 31" with a higher activation for "March 31" specifically

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 31

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atis
    -0.86
    atics
    -0.85
    abwe
    -0.85
    akens
    -0.78
    atic
    -0.78
    akespe
    -0.76
    fare
    -0.71
    yrinth
    -0.71
    anned
    -0.70
    awaru
    -0.70
    POSITIVE LOGITS
    st
    0.93
    ¯¯
    0.75
    rd
    0.72
    ¯¯¯¯
    0.70
    00
    0.69
    803
    0.67
    bow
    0.65
     msec
    0.64
    ESS
    0.64
    backer
    0.63
    Act Density 0.041%

    No Known Activations