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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical errors or malfunctions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating errors or technical problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ashes
    -0.69
    thora
    -0.69
    âĸij
    -0.67
    cott
    -0.66
    amy
    -0.64
    aterasu
    -0.62
    cedes
    -0.62
     boils
    -0.61
    wives
    -0.60
    emouth
    -0.59
    POSITIVE LOGITS
    interstitial
    0.74
    Asset
    0.73
    Registration
    0.69
     Reload
    0.67
    Register
    0.63
     Newsletter
    0.62
     Message
    0.62
     Registration
    0.61
     Reporting
    0.61
     Please
    0.60
    Act Density 0.045%

    No Known Activations