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

    Neuronpedia

    INDEX
    Explanations

    verbs relating to possession or action, typically associated with the subject followed by an apostrophe and the letter 's'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ren
    -0.67
    ESE
    -0.67
    ={
    -0.66
    DS
    -0.63
    sen
    -0.62
    ansas
    -0.62
    roit
    -0.62
    TAIN
    -0.61
    ollow
    -0.61
    scope
    -0.61
    POSITIVE LOGITS
     gotta
    1.41
     gonna
    1.33
     got
    1.18
     been
    1.13
     gotten
    1.07
    been
    0.93
     Been
    0.90
     supposed
    0.89
     going
    0.86
     gone
    0.84
    Act Density 0.519%

    No Known Activations