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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe qualities and characteristics of things, particularly in a creative or artistic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tables
    -0.17
    orer
    -0.17
    thing
    -0.15
    _emails
    -0.15
     its
    -0.15
     Talks
    -0.15
    å®ĥ
    -0.15
    otope
    -0.15
     Committees
    -0.15
     Panels
    -0.14
    POSITIVE LOGITS
     ones
    0.34
     targets
    0.31
     themselves
    0.30
     sources
    0.30
     entities
    0.28
     objects
    0.27
     examples
    0.27
     substitutes
    0.27
     additions
    0.27
     assets
    0.25
    Act Density 0.507%

    No Known Activations