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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reputation or recognition of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urga
    -0.15
    blas
    -0.14
    uggage
    -0.14
    Formats
    -0.14
     Vander
    -0.13
    lements
    -0.13
    éĺħ读次æķ°
    -0.13
    yses
    -0.13
    /Area
    -0.13
    åĬŁ
    -0.13
    POSITIVE LOGITS
    edo
    0.17
     reb
    0.15
     Millet
    0.15
    ÑĤап
    0.14
    edly
    0.14
    ably
    0.14
     its
    0.14
    صÙĩ
    0.14
    ÑĢин
    0.14
     ac
    0.14
    Act Density 0.043%

    No Known Activations