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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to positivity and brightness

    oai_token-act-pair · gpt-3.5-turbo

    references to brightness or positive connotations associated with the word "bright."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilage
    -0.70
    trl
    -0.66
     intimately
    -0.64
    oths
    -0.63
    utor
    -0.62
    emetery
    -0.61
    yip
    -0.61
    ratom
    -0.60
    ensis
    -0.60
    $$$$
    -0.60
    POSITIVE LOGITS
    ening
    1.31
    ened
    1.28
    eners
    1.19
    ener
    1.12
     lights
    0.98
     eyed
    0.96
    lights
    0.95
    eyed
    0.94
     sunlight
    0.89
    light
    0.89
    Act Density 0.031%

    No Known Activations