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

    Neuronpedia

    INDEX
    Explanations

    adjectives referring to quality or significance

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptive phrases that convey significant emotional or evaluative weight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneers
    -0.91
    »Ĵ
    -0.81
    IDES
    -0.80
    ahs
    -0.79
    icons
    -0.78
    dor
    -0.76
    racuse
    -0.76
    endants
    -0.74
    viks
    -0.74
    onds
    -0.72
    POSITIVE LOGITS
     territory
    1.27
     fodder
    1.08
     stuff
    1.07
     nonsense
    1.04
     enough
    1.04
     insanity
    0.97
     behavior
    0.97
     advice
    0.94
     folly
    0.93
     stupidity
    0.93
    Act Density 0.306%

    No Known Activations