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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ren
    -0.67
    sen
    -0.66
    ={
    -0.65
    ESE
    -0.64
    roit
    -0.63
    TAIN
    -0.62
    \/
    -0.61
    scope
    -0.61
    cos
    -0.61
    ·
    -0.61
    POSITIVE LOGITS
     gotta
    1.49
     gonna
    1.34
     got
    1.24
     been
    1.13
     gotten
    1.10
    been
    0.95
     Been
    0.93
     gone
    0.85
     going
    0.81
     supposed
    0.78
    Act Density 1.231%

    No Known Activations