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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    sentences that emphasize the subject "It" and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eighth
    -0.64
    hips
    -0.62
    EngineDebug
    -0.59
    natureconservancy
    -0.59
     NX
    -0.58
    Finish
    -0.58
     guiActiveUnfocused
    -0.58
    duc
    -0.58
    package
    -0.56
     Siri
    -0.56
    POSITIVE LOGITS
    self
    1.06
    unes
    1.05
    iner
    1.00
    zbollah
    0.96
    achi
    0.95
    amar
    0.91
    xtap
    0.89
     certainly
    0.89
    chy
    0.88
    'll
    0.88
    Act Density 0.200%

    No Known Activations