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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific concepts, terms, or laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hesda
    -0.73
     inclined
    -0.71
    etheless
    -0.66
     muted
    -0.66
     hesitant
    -0.65
     faculties
    -0.65
     tempted
    -0.64
     disarm
    -0.64
     truthful
    -0.64
    aples
    -0.63
    POSITIVE LOGITS
    "—
    0.76
    ".
    0.75
     Kare
    0.72
     Geh
    0.72
    ",
    0.71
    *.
    0.69
     Versus
    0.68
    Emer
    0.66
    itis
    0.65
    Cop
    0.65
    Act Density 0.580%

    No Known Activations