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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uj
    -0.17
    ongs
    -0.17
    irs
    -0.16
     дан
    -0.15
    ungs
    -0.15
     íķ´ëĭ¹
    -0.15
    osh
    -0.14
    onom
    -0.14
    ilon
    -0.14
    hung
    -0.14
    POSITIVE LOGITS
     eso
    0.57
     isso
    0.48
     cela
    0.46
     Ø°ÙĦÙĥ
    0.42
     THAT
    0.41
     ello
    0.40
     ça
    0.38
     esto
    0.37
     Äijó
    0.37
     váºŃy
    0.36
    Act Density 0.574%

    No Known Activations