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

    Neuronpedia

    INDEX
    Explanations

    phrases related to words starting or ending with "aw"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific regions or areas associated with energy production and megawatts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Luther
    -0.73
     Luthor
    -0.70
     Juda
    -0.65
     Mayhem
    -0.63
     Clown
    -0.63
    matter
    -0.62
    ãĤ¹ãĥĪ
    -0.61
     unpre
    -0.60
     VK
    -0.59
     Archdemon
    -0.58
    POSITIVE LOGITS
    esome
    1.50
    akening
    1.30
    aii
    1.21
    yer
    1.12
    kward
    1.12
    orld
    1.08
    akens
    1.06
    ashington
    1.06
    orks
    1.06
    yers
    0.97
    Act Density 0.033%

    No Known Activations