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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases related to alerts and notifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to alerts or notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ogre
    -0.72
    atan
    -0.72
    dx
    -0.67
    puff
    -0.66
    Plex
    -0.66
     ABE
    -0.65
     Jinn
    -0.64
    APH
    -0.63
    76561
    -0.63
    Cube
    -0.62
    POSITIVE LOGITS
     alert
    0.97
    gency
    0.88
    ingly
    0.86
     alerts
    0.82
    ness
    0.78
     Alert
    0.75
    ibility
    0.75
     alerted
    0.73
    ilogy
    0.72
    mares
    0.71
    Act Density 0.015%

    No Known Activations