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

    Neuronpedia

    INDEX
    Explanations

    suspicious activities in various scenarios

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsen
    -0.83
    ffen
    -0.73
    arium
    -0.69
    ĸļ
    -0.68
    ophon
    -0.68
    á
    -0.68
     taught
    -0.66
    agos
    -0.66
     apologise
    -0.66
    bourg
    -0.66
    POSITIVE LOGITS
    ly
    1.05
     Activity
    1.04
     activity
    1.00
     Intent
    0.88
     motives
    0.86
     intent
    0.85
     behaviour
    0.83
     behavior
    0.81
     behaviours
    0.78
    icious
    0.78
    Act Density 0.045%

    No Known Activations