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

    Neuronpedia

    INDEX
    Explanations

    items related to rankings or positions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    facts
    -0.76
    evidence
    -0.71
    Enjoy
    -0.66
    Contents
    -0.65
    letters
    -0.65
    guards
    -0.64
     Dates
    -0.64
     Amend
    -0.64
    rules
    -0.62
    lest
    -0.62
    POSITIVE LOGITS
     standpoint
    1.41
     vantage
    1.15
     perspective
    1.08
     distance
    0.97
     viewpoint
    0.95
     variety
    0.87
     helicopter
    0.79
     outset
    0.79
     perspect
    0.78
     POV
    0.76
    Act Density 0.049%

    No Known Activations