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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting or urging action

    oai_token-act-pair · gpt-3.5-turbo

    questions and prompts that invite action or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occupation
    -0.81
     angered
    -0.80
     anomal
    -0.79
     perce
    -0.77
     sustained
    -0.76
     alleged
    -0.74
     hospitalized
    -0.74
     disturbed
    -0.74
     perceived
    -0.74
     inco
    -0.73
    POSITIVE LOGITS
     ;)
    1.42
     ðŁĻĤ
    1.34
     :)
    1.30
     Simply
    1.22
     :-)
    1.14
     Enjoy
    1.13
     ðŁĺ
    1.12
     You
    1.11
     Besides
    1.09
     Anyway
    1.08
    Act Density 0.631%

    No Known Activations