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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being stuck or trapped

    oai_token-act-pair · gpt-3.5-turbo

    past participles and forms of verbs indicating a passive or trapped state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellar
    -0.62
    Balt
    -0.61
    antz
    -0.60
    NT
    -0.60
    Labor
    -0.59
    Nap
    -0.58
     datas
    -0.57
    RB
    -0.57
    vor
    -0.56
    ortium
    -0.55
    POSITIVE LOGITS
     by
    0.99
     BY
    0.87
    ĸļ
    0.83
    uled
    0.81
     aback
    0.79
    abouts
    0.79
    monton
    0.75
    igger
    0.70
     merciless
    0.69
    igated
    0.68
    Act Density 0.093%

    No Known Activations