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

    Neuronpedia

    INDEX
    Explanations

    terms related to the creation or generation of various things

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the creation or establishment of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itsch
    -0.70
     expressing
    -0.63
    tes
    -0.61
     WATCHED
    -0.59
    words
    -0.57
     Wit
    -0.56
    bid
    -0.55
    fle
    -0.55
     rendered
    -0.54
    speaking
    -0.54
    POSITIVE LOGITS
     havoc
    1.21
     opportunities
    0.97
     friction
    0.93
     incentives
    0.90
     confusion
    0.84
     uproar
    0.82
     openings
    0.81
     instability
    0.80
    idable
    0.77
     opportunity
    0.76
    Act Density 0.106%

    No Known Activations