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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons and contrasts in performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zyst
    -0.16
    nish
    -0.15
    oker
    -0.15
     itself
    -0.14
    bolt
    -0.14
    è¦
    -0.14
     mist
    -0.14
     nÃło
    -0.14
    egra
    -0.13
    यर
    -0.13
    POSITIVE LOGITS
     respectively
    0.49
     alike
    0.36
    åĪĨåĪ«
    0.32
     respective
    0.32
     ê°ģê°ģ
    0.28
     ÑģооÑĤвеÑĤ
    0.24
    respect
    0.23
     beide
    0.22
    ãģĿãĤĮ
    0.21
     both
    0.18
    Act Density 0.502%

    No Known Activations