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

    Neuronpedia

    INDEX
    Explanations

    numbers related to technical specifications or benchmarks

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those associated with specifications or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.87
     separat
    -0.67
    vity
    -0.66
    coat
    -0.64
    houses
    -0.63
     adolesc
    -0.62
     Vend
    -0.62
    lier
    -0.61
    amide
    -0.61
     millenn
    -0.60
    POSITIVE LOGITS
    00
    0.96
    rd
    0.87
    dfx
    0.79
    491
    0.79
    017
    0.78
    007
    0.77
    70
    0.76
    sey
    0.76
    01
    0.74
    RD
    0.74
    Act Density 0.119%

    No Known Activations