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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rates or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical rates or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aires
    -0.83
    IRT
    -0.82
    NetMessage
    -0.82
    iami
    -0.78
    ADRA
    -0.76
    enegger
    -0.74
    bley
    -0.73
    ë
    -0.72
    yssey
    -0.71
    ymm
    -0.70
    POSITIVE LOGITS
    payers
    1.22
    payer
    1.08
     rate
    1.02
    Rate
    0.94
     rates
    0.91
     Rate
    0.86
    abilities
    0.79
    hyde
    0.79
     ratio
    0.77
     ratios
    0.76
    Act Density 0.022%

    No Known Activations