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

    Neuronpedia

    INDEX
    Explanations

    mentions of disturbances or things that are disturbing

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to disturbance or distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uay
    -0.82
    ardi
    -0.79
    hler
    -0.74
    arde
    -0.74
    tin
    -0.73
    á
    -0.73
    veland
    -0.72
    elsen
    -0.71
    HER
    -0.70
    cellence
    -0.70
    POSITIVE LOGITS
    ingly
    0.89
     Trend
    0.67
     signals
    0.66
     behaviour
    0.66
     Enlightenment
    0.66
     behaviours
    0.64
     Territories
    0.62
     Geo
    0.61
     behaviors
    0.60
     neighbours
    0.60
    Act Density 0.064%

    No Known Activations