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

    Neuronpedia

    INDEX
    Explanations

    dates formatted as month/day/year

    oai_token-act-pair · gpt-3.5-turbo

    numbers and date-like formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.93
    uese
    -0.87
    accompan
    -0.80
    ãĤ©
    -0.75
    oshenko
    -0.75
    ongyang
    -0.73
    ©¶æ
    -0.73
    ãĤ£
    -0.72
    otto
    -0.71
    retty
    -0.70
    POSITIVE LOGITS
    enegger
    0.85
     Wonderland
    0.70
    displayText
    0.68
    ottest
    0.62
    kamp
    0.62
     Rue
    0.61
     Jah
    0.61
    bush
    0.60
     Simulator
    0.60
     Vers
    0.59
    Act Density 0.226%

    No Known Activations