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

    Neuronpedia

    INDEX
    Explanations

    the word "you" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HING
    -0.15
    ington
    -0.14
    aukee
    -0.14
    YLES
    -0.14
    stoff
    -0.14
    íĥĦ
    -0.14
     Rein
    -0.14
     Pf
    -0.13
    íĮ
    -0.13
    amax
    -0.13
    POSITIVE LOGITS
    -même
    0.23
    zelf
    0.20
    /us
    0.19
    adic
    0.16
    itable
    0.15
     Spicer
    0.15
    uld
    0.15
     Norm
    0.15
     guys
    0.14
    ixe
    0.14
    Act Density 0.093%

    No Known Activations