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

    Neuronpedia

    INDEX
    Explanations

    words related to light

    oai_token-act-pair · gpt-3.5-turbo

    references to light

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    halla
    -0.84
    berus
    -0.80
     Carnegie
    -0.70
    JUST
    -0.69
    utor
    -0.69
     Bagg
    -0.67
    CVE
    -0.66
    uador
    -0.66
     Mellon
    -0.66
    OUP
    -0.65
    POSITIVE LOGITS
    bul
    1.35
    hearted
    1.34
    ening
    1.31
    weights
    1.29
    nings
    1.26
    weight
    1.23
     bulb
    1.20
    ning
    1.17
     bulbs
    1.15
    enment
    1.12
    Act Density 0.037%

    No Known Activations