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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to data analysis and statistics

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to measurements, evaluations, and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ª
    -0.51
     unmist
    -0.50
     Hanna
    -0.50
     routed
    -0.49
     stark
    -0.49
     startled
    -0.48
     bright
    -0.48
    guyen
    -0.47
    advert
    -0.47
     closest
    -0.47
    POSITIVE LOGITS
    .</
    0.98
    !.
    0.92
    .[
    0.92
    .'
    0.92
    .(
    0.91
    .<
    0.91
    '.
    0.90
    .}
    0.90
    .''.
    0.88
    .]
    0.88
    Act Density 1.120%

    No Known Activations