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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dismissal or indifference towards something in a given context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     stead
    -0.69
    ebus
    -0.66
     livest
    -0.64
     destro
    -0.64
     foothold
    -0.61
     streng
    -0.60
    greSQL
    -0.60
     crawl
    -0.59
    ppa
    -0.59
     ingred
    -0.59
    POSITIVE LOGITS
    otom
    0.83
    ively
    0.81
    igated
    0.77
     aside
    0.77
    als
    0.77
     outright
    0.77
    iated
    0.75
    ument
    0.74
     dismiss
    0.73
    igating
    0.72
    Act Density 0.027%

    No Known Activations