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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical structures and their conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to physical damage and destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.59
     Insider
    -0.58
    ãĥīãĥ©ãĤ´ãĥ³
    -0.56
    $$$$
    -0.55
    uably
    -0.53
    enegger
    -0.53
    "]=>
    -0.52
    ourke
    -0.52
    Guest
    -0.51
    ERO
    -0.49
    POSITIVE LOGITS
     stret
    0.66
     exha
    0.64
    worms
    0.62
     tubes
    0.61
     ropes
    0.61
     debris
    0.60
    worm
    0.59
     cones
    0.59
     mound
    0.59
     trough
    0.59
    Act Density 2.043%

    No Known Activations