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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лок
    -0.15
     Hao
    -0.15
     ten
    -0.14
     Rose
    -0.14
     Matte
    -0.14
     unit
    -0.14
    isse
    -0.14
    ech
    -0.14
    Reuse
    -0.14
    çļ
    -0.14
    POSITIVE LOGITS
    uder
    0.16
    _consts
    0.15
    rive
    0.15
    ocu
    0.14
    _vert
    0.14
    nika
    0.14
     Dear
    0.14
     olursa
    0.14
    lamaz
    0.14
    uerdo
    0.14
    Act Density 0.021%

    No Known Activations