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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verb phrases related to teamwork and cooperation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "they" and expressions of group dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.74
     Surveillance
    -0.65
    pires
    -0.65
    channelAvailability
    -0.65
     airing
    -0.62
     Adds
    -0.62
     suspending
    -0.61
     granting
    -0.60
     Cancel
    -0.59
    powers
    -0.59
    POSITIVE LOGITS
     knew
    1.44
     tended
    1.41
     lacked
    1.40
     wore
    1.37
     didn
    1.36
     hadn
    1.31
     resembled
    1.29
     depended
    1.28
     cared
    1.25
     had
    1.25
    Act Density 0.816%

    No Known Activations