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

    Neuronpedia

    INDEX
    Explanations

    actions related to meeting, discussing, and working with others

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to meetings and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prev
    -0.67
    irection
    -0.66
     equivalents
    -0.62
     Tsukuyomi
    -0.62
     inconsist
    -0.62
     sued
    -0.61
     downward
    -0.61
     suicide
    -0.61
     abandonment
    -0.60
    TPS
    -0.60
    POSITIVE LOGITS
     discuss
    1.38
     reminis
    1.22
     acquaint
    1.16
     learn
    1.12
     unveil
    1.07
     talk
    1.06
     showcase
    1.04
     congratulate
    1.03
     brainstorm
    1.03
     observe
    1.00
    Act Density 0.631%

    No Known Activations