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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate personal relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urban
    -0.15
    annie
    -0.14
    ű
    -0.14
    rug
    -0.13
    sut
    -0.13
    оÑĢÑĥ
    -0.13
    WithTag
    -0.13
    RIPT
    -0.13
     eg
    -0.13
    irie
    -0.13
    POSITIVE LOGITS
     himself
    0.20
    ioned
    0.16
     Himself
    0.16
     herself
    0.16
     ÙĨÙģسÙĩ
    0.16
    ãģĹãĤĩ
    0.15
     molec
    0.14
    iana
    0.13
    poke
    0.13
    itesse
    0.13
    Act Density 0.555%

    No Known Activations