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

    Neuronpedia

    INDEX
    Explanations

    expressions or patterns related to coding or programming

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 42

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.92
    icago
    -0.89
    jriwal
    -0.86
    kered
    -0.78
    ailand
    -0.77
    otaur
    -0.77
    itent
    -0.76
    oppy
    -0.76
     temptation
    -0.75
     prosec
    -0.75
    POSITIVE LOGITS
    APH
    0.86
    50
    0.83
    RD
    0.80
    OGR
    0.80
    41
    0.78
    80
    0.75
    44
    0.75
    00
    0.75
    42
    0.73
    %-
    0.72
    Act Density 0.031%

    No Known Activations