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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal impact and consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to impact and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /?
    -0.59
    },
    -0.55
     Became
    -0.55
    umar
    -0.54
     Reports
    -0.52
     Applications
    -0.51
    myra
    -0.50
     proposed
    -0.49
     Introduced
    -0.49
     largeDownload
    -0.49
    POSITIVE LOGITS
     neither
    1.21
     everywhere
    1.16
    only
    1.15
     EVERY
    1.14
     nonetheless
    1.10
     scarcely
    1.09
     hardly
    1.09
     both
    1.08
     nowhere
    1.06
     only
    1.06
    Act Density 1.701%

    No Known Activations