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

    Neuronpedia

    INDEX
    Explanations

    hyphenated third-party terms

    oai_token-act-pair · gpt-3.5-turbo

    references to third-party entities and their involvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.78
     Richards
    -0.75
     Paradox
    -0.73
    utical
    -0.72
    pload
    -0.72
     Lovecraft
    -0.71
    ãĤ¡
    -0.70
     Canaver
    -0.70
     Arabian
    -0.70
    Ń·
    -0.68
    POSITIVE LOGITS
    degree
    1.20
    eyed
    1.16
    party
    1.14
    dimensional
    1.13
    level
    1.09
    ranked
    1.09
    chance
    1.08
    century
    1.08
    generation
    1.05
    year
    1.02
    Act Density 0.043%

    No Known Activations