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

    Neuronpedia

    INDEX
    Explanations

    words related to warnings or notifications

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to alerts and notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cca
    -0.82
    ç¥ŀ
    -0.80
    ADA
    -0.75
    çĶ°
    -0.71
    Plex
    -0.69
    ãĤ°
    -0.68
     ABE
    -0.68
    ãģĤ
    -0.68
    BU
    -0.66
    BALL
    -0.66
    POSITIVE LOGITS
     Alert
    1.29
    icter
    0.96
    Alert
    0.93
    icons
    0.82
     Monitor
    0.78
     alert
    0.77
    ness
    0.75
    oreAnd
    0.75
    ogether
    0.72
    ingly
    0.71
    Act Density 0.007%

    No Known Activations