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

    Neuronpedia

    INDEX
    Explanations

    website-related instructions and links

    oai_token-act-pair · gpt-3.5-turbo

    references to websites and official sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.79
    Ò
    -0.78
     forcibly
    -0.68
    ictions
    -0.66
    ingly
    -0.64
    ãĥĺ
    -0.64
    .''
    -0.64
    itar
    -0.63
    ãĤ¼
    -0.62
    ogenic
    -0.62
    POSITIVE LOGITS
     following
    1.12
     sidebar
    1.06
     respective
    1.05
     aforementioned
    0.97
     FAQ
    0.96
     corresponding
    0.94
     References
    0.94
     homepage
    0.93
     bottom
    0.89
     nearest
    0.89
    Act Density 0.159%

    No Known Activations