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

    Neuronpedia

    INDEX
    Explanations

    mentions of asking questions or seeking information

    oai_token-act-pair · gpt-3.5-turbo

    repeated directives or questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     restraint
    -0.70
     supported
    -0.66
    onents
    -0.66
     dissip
    -0.65
    velop
    -0.65
     gross
    -0.64
     comple
    -0.64
     spl
    -0.63
     multiplier
    -0.63
     weapon
    -0.63
    POSITIVE LOGITS
     Ask
    3.48
    Ask
    3.28
     AMA
    1.44
    ask
    1.41
     Answers
    1.24
    meet
    1.16
     Speak
    1.16
     Questions
    1.15
     Tell
    1.10
     Answer
    1.05
    Act Density 0.010%

    No Known Activations