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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a call to action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of maintaining awareness or continuous engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.70
    女
    -0.70
    ody
    -0.70
    odied
    -0.68
     tom
    -0.68
    displayText
    -0.67
    ointed
    -0.64
    OUN
    -0.63
    Nich
    -0.62
     GOODMAN
    -0.61
    POSITIVE LOGITS
     tabs
    0.89
    overs
    0.85
    chin
    0.80
    ership
    0.78
     Calm
    0.78
     pace
    0.75
    ers
    0.74
     scrolling
    0.74
    agh
    0.73
    watch
    0.73
    Act Density 0.030%

    No Known Activations