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

    Neuronpedia

    INDEX
    Explanations

    references to familial and possessive pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gratuit
    -0.16
    ãģĹãĤĩ
    -0.15
     Consortium
    -0.15
    ÑģÑĤве
    -0.15
    exus
    -0.14
    Ñģов
    -0.14
    ucu
    -0.14
    essen
    -0.14
    еÑĢин
    -0.14
    TES
    -0.13
    POSITIVE LOGITS
     own
    0.17
    ãĥ¼ãĥ¬
    0.17
    own
    0.16
    pler
    0.15
    ewe
    0.14
     ga
    0.14
    URITY
    0.14
     atof
    0.14
    ement
    0.14
    bye
    0.14
    Act Density 0.240%

    No Known Activations