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

    Neuronpedia

    INDEX
    Explanations

    references to the human body and its various states or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Deaths
    -0.84
     Supporters
    -0.72
     Nights
    -0.69
     Crim
    -0.68
     Pipe
    -0.67
     Badge
    -0.67
     Mous
    -0.66
     Flight
    -0.66
     Squadron
    -0.65
     Orn
    -0.64
    POSITIVE LOGITS
     reacting
    0.93
     reacts
    0.84
     adapting
    0.78
     perce
    0.74
     adapt
    0.74
    ierrez
    0.72
     instinctively
    0.72
     transitioning
    0.71
    folk
    0.71
    ournal
    0.70
    Act Density 0.206%

    No Known Activations