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

    Neuronpedia

    INDEX
    Explanations

    references to exposure and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ainfi
    -0.61
    IVEREF
    -0.52
    MENAFN
    -0.52
     demikian
    -0.51
     zelve
    -0.50
     betweenstory
    -0.50
     llorar
    -0.50
     nė
    -0.49
     larmes
    -0.48
     soulign
    -0.48
    POSITIVE LOGITS
     exposure
    1.98
     Exposure
    1.80
    Exposure
    1.80
    exposure
    1.70
     EXPOSURE
    1.66
     exposed
    1.63
     exposures
    1.52
     expose
    1.48
    exposed
    1.48
     Exposed
    1.38
    Act Density 0.257%

    No Known Activations