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

    Neuronpedia

    INDEX
    Explanations

    mention of being kicked out of a place or situation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilies
    -0.75
    uncture
    -0.69
    Card
    -0.69
    buquerque
    -0.62
    Benef
    -0.62
    aeus
    -0.61
    Applic
    -0.61
     Pend
    -0.60
    etta
    -0.59
     Returning
    -0.59
    POSITIVE LOGITS
     unnoticed
    0.95
     sidx
    0.75
     stairs
    0.74
     shopping
    0.73
    wagon
    0.73
     overboard
    0.71
     raft
    0.70
     lengths
    0.70
     undet
    0.69
    WARD
    0.68
    Act Density 0.180%

    No Known Activations