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

    Neuronpedia

    INDEX
    Explanations

    specific individuals and entities, particularly in the context of conflicts or social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rió
    -0.18
    ió
    -0.15
    annis
    -0.15
    posables
    -0.15
    orex
    -0.15
    Occurred
    -0.14
    ould
    -0.14
    ÅĻÃŃz
    -0.14
    pio
    -0.14
    nown
    -0.14
    POSITIVE LOGITS
     being
    0.29
    being
    0.22
     becoming
    0.19
     Being
    0.19
    Being
    0.17
     having
    0.17
    's
    0.17
     sendo
    0.17
     getting
    0.17
    ’s
    0.17
    Act Density 0.213%

    No Known Activations