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

    Neuronpedia

    INDEX
    Explanations

    topics related to community, interpersonal relationships, and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.21
     himself
    -0.20
    ç»ĻæĪij
    -0.20
     itself
    -0.20
     us
    -0.19
    让æĪij
    -0.16
    itta
    -0.15
    egative
    -0.15
    .compiler
    -0.14
    оÑĩ
    -0.14
    POSITIVE LOGITS
     ourselves
    0.68
    ours
    0.29
    Ñħодим
    0.29
     abych
    0.29
     our
    0.28
     наÑĪиÑħ
    0.25
     jsme
    0.23
    æĪij们çļĦ
    0.23
     мож
    0.23
    ï¼ĮæĪij们
    0.22
    Act Density 1.714%

    No Known Activations