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

    Neuronpedia

    INDEX
    Explanations

    instances of confusion or uncertainty related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unya
    -0.16
    tak
    -0.16
     Mirage
    -0.15
    zos
    -0.15
    ughs
    -0.15
    lé
    -0.14
    ãĥ³ãĤ¹
    -0.14
    irst
    -0.14
    manship
    -0.14
     Wy
    -0.14
    POSITIVE LOGITS
    /conf
    0.32
     confusion
    0.27
     confuse
    0.25
     confusing
    0.23
     confused
    0.21
     Conf
    0.18
    ingly
    0.18
     conf
    0.17
    ly
    0.16
    Conf
    0.16
    Act Density 0.039%

    No Known Activations