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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting social interaction or participation

    oai_token-act-pair · gpt-3.5-turbo

    calls to action for joining or participating in activities or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pap
    -0.68
     omn
    -0.66
     defenses
    -0.64
     controlling
    -0.64
     crude
    -0.64
     ballistic
    -0.63
     suppressed
    -0.62
     defense
    -0.61
     reception
    -0.61
     satisfactory
    -0.60
    POSITIVE LOGITS
    Join
    4.30
     Join
    2.57
    join
    1.97
    Joined
    1.59
     join
    1.42
    Explore
    1.25
    joining
    1.23
    Subscribe
    1.22
    Meet
    1.18
    Submit
    1.17
    Act Density 0.006%

    No Known Activations