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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to brightness

    oai_token-act-pair · gpt-3.5-turbo

    the word "bright" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trl
    -0.74
    ossession
    -0.73
    HAEL
    -0.73
    uberty
    -0.72
    undle
    -0.71
    ilage
    -0.71
    GAN
    -0.71
    utor
    -0.69
    obic
    -0.68
     intimately
    -0.67
    POSITIVE LOGITS
    ening
    1.28
    ened
    1.28
    eners
    1.18
    ener
    1.07
     lights
    0.99
     bright
    0.93
    lights
    0.91
    eyed
    0.90
    lighting
    0.89
     brighter
    0.89
    Act Density 0.017%

    No Known Activations