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

    Neuronpedia

    INDEX
    Explanations

    mentions of camaraderie or teamwork within a group

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people, often in a social or community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tains
    -0.77
    ¿½
    -0.64
     Flavoring
    -0.64
    iHUD
    -0.64
    Increases
    -0.62
    YL
    -0.62
     Windsor
    -0.60
     concluding
    -0.59
    azard
    -0.59
     Prel
    -0.59
    POSITIVE LOGITS
     aren
    1.60
     deserve
    1.44
     are
    1.40
     weren
    1.37
     ARE
    1.36
     don
    1.35
     suck
    1.34
     ain
    1.33
     gotta
    1.33
     dont
    1.31
    Act Density 0.419%

    No Known Activations