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

    Neuronpedia

    INDEX
    Explanations

    phrases related to innovation, new ways of doing things, and different kinds of approaches

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing innovative approaches or new methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WATCHED
    -0.70
    ogun
    -0.70
    wolves
    -0.66
    ocado
    -0.66
    umps
    -0.65
    ongyang
    -0.63
     retracted
    -0.62
    omer
    -0.62
    akespeare
    -0.62
    oret
    -0.62
    POSITIVE LOGITS
    worldly
    0.86
     sensations
    0.72
     altogether
    0.71
     than
    0.69
     perspective
    0.68
     perspectives
    0.63
    thinking
    0.62
     ze
    0.61
     combining
    0.61
     sensation
    0.61
    Act Density 0.193%

    No Known Activations