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

    Neuronpedia

    INDEX
    Explanations

    possessive forms and references to possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¿ĥ
    -0.14
     himself
    -0.14
     resigned
    -0.14
    帰
    -0.14
     personally
    -0.13
    his
    -0.13
    ispers
    -0.13
     resh
    -0.13
     testim
    -0.13
    quot
    -0.13
    POSITIVE LOGITS
     own
    0.20
     itself
    0.19
     finest
    0.18
     newest
    0.17
    unsch
    0.17
     Its
    0.15
     its
    0.15
     latest
    0.15
     ê²½ìļ°
    0.15
    leurs
    0.14
    Act Density 0.124%

    No Known Activations