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

    Neuronpedia

    INDEX
    Explanations

    terms related to catastrophic events or high-energy phenomena

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tidal phenomena and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orate
    -0.70
    elf
    -0.69
    enegger
    -0.67
    oken
    -0.67
    è¦ļéĨĴ
    -0.66
     Dying
    -0.65
    raised
    -0.65
    raising
    -0.64
     Broken
    -0.61
    eon
    -0.60
    POSITIVE LOGITS
    idal
    1.62
    itor
    0.74
    vier
    0.71
    atory
    0.71
     pend
    0.70
    oad
    0.70
    adoes
    0.68
    otine
    0.68
    ãĥ¥
    0.67
    onda
    0.67
    Act Density 0.007%

    No Known Activations