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

    Neuronpedia

    INDEX
    Explanations

    dates presented in the format of month and year

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 15 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atis
    -0.78
    nih
    -0.67
     reborn
    -0.66
    itsch
    -0.64
    ascus
    -0.64
    ei
    -0.62
    umin
    -0.61
    edia
    -0.61
    pora
    -0.60
    omial
    -0.60
    POSITIVE LOGITS
    th
    0.94
     Minutes
    0.86
     minutes
    0.84
    555
    0.83
    mins
    0.81
    55
    0.80
    985
    0.79
    nm
    0.78
    arters
    0.78
    ances
    0.77
    Act Density 0.101%

    No Known Activations