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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and importance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fte
    -1.02
     ?...
    -0.99
     secon
    -0.95
     wald
    -0.94
     idr
    -0.94
     wien
    -0.94
     fta
    -0.94
     §.
    -0.94
     fff
    -0.94
     oun
    -0.93
    POSITIVE LOGITS
     difference
    0.63
    venser
    0.54
    difference
    0.50
    setToolTip
    0.49
    twimg
    0.47
     차
    0.46
     helps
    0.45
     diferença
    0.45
     lot
    0.45
     createSlice
    0.45
    Act Density 0.184%

    No Known Activations