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

    Neuronpedia

    INDEX
    Explanations

    expressions of social interactions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.18
    jon
    -0.18
    hoa
    -0.17
    æĹıèĩªæ²»
    -0.16
     frags
    -0.16
    dea
    -0.15
    stal
    -0.14
    gel
    -0.14
    üy
    -0.14
     дÑĢÑĥ
    -0.14
    POSITIVE LOGITS
     dance
    0.57
     dancing
    0.51
     dances
    0.51
     danced
    0.50
     Dance
    0.47
    dance
    0.46
     dancers
    0.43
     Dancing
    0.42
     dancer
    0.39
     ÑĤан
    0.34
    Act Density 0.076%

    No Known Activations