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

    Neuronpedia

    INDEX
    Explanations

    different expressions or references to "face" and "way."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    568
    -0.16
     sque
    -0.15
    pez
    -0.15
     Zap
    -0.15
    loh
    -0.14
    aque
    -0.14
    mary
    -0.13
     figure
    -0.13
     against
    -0.13
     bur
    -0.13
    POSITIVE LOGITS
    rieve
    0.17
    mpp
    0.16
    ãĥĵãĥ¼
    0.15
     crown
    0.15
    еÑĢин
    0.14
    mented
    0.14
    gin
    0.14
    ÑģÑĤин
    0.14
     krev
    0.14
    ĽĪ
    0.14
    Act Density 0.253%

    No Known Activations