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

    instances of the word "light."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    halla
    -0.92
    utor
    -0.78
    berus
    -0.77
    ettings
    -0.76
    052
    -0.72
    CVE
    -0.71
     Carnegie
    -0.70
    OUP
    -0.69
     Bagg
    -0.68
     Forbidden
    -0.67
    POSITIVE LOGITS
    bul
    1.29
    weights
    1.27
    ening
    1.27
    hearted
    1.25
     bulb
    1.18
    nings
    1.17
    enment
    1.14
     bulbs
    1.10
    eners
    1.10
    ened
    1.09
    Act Density 0.041%

    No Known Activations