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

    Neuronpedia

    INDEX
    Explanations

    verbs describing being or existence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rones
    -0.77
     cease
    -0.67
     compose
    -0.66
    culosis
    -0.63
    ĸļ
    -0.63
     promise
    -0.62
     roam
    -0.61
     Rab
    -0.61
     occupy
    -0.61
     mark
    -0.61
    POSITIVE LOGITS
     viewed
    1.14
     considered
    1.09
     construed
    1.09
     regarded
    1.06
     traced
    1.02
     likened
    1.01
     forgiven
    1.01
     seen
    1.00
     able
    0.98
    fitting
    0.97
    Act Density 0.999%

    No Known Activations