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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     administr
    -0.83
     manif
    -0.81
     purs
    -0.70
     Vaugh
    -0.66
    orno
    -0.66
     arrang
    -0.66
     withd
    -0.65
     unim
    -0.65
     neighb
    -0.64
     tradem
    -0.63
    POSITIVE LOGITS
     SHARES
    0.86
     Expand
    0.78
     ][
    0.76
     ·
    0.75
     Lessons
    0.74
    RF
    0.73
     Minutes
    0.73
    80
    0.71
     Updated
    0.71
    89
    0.71
    Act Density 0.085%

    No Known Activations