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

    Neuronpedia

    INDEX
    Explanations

    names and mentions of celebrities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    transQ
    -0.47
    heça
    -0.44
     exposiciones
    -0.43
     invokingState
    -0.41
     journées
    -0.41
     progrès
    -0.39
     práctico
    -0.39
     mandiri
    -0.38
     capucha
    -0.38
     ouvert
    -0.38
    POSITIVE LOGITS
     celebrity
    0.73
     celebrities
    0.73
     celebs
    0.69
     superstar
    0.65
    celebrity
    0.65
     يتيمه
    0.63
    BeginContext
    0.63
     superstars
    0.60
     فريبيس
    0.57
     Celebrity
    0.57
    Act Density 0.334%

    No Known Activations