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

    Neuronpedia

    INDEX
    Explanations

    checkboxes that need to be clicked to confirm non-robotic behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to user interaction elements, particularly checkboxes and buttons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -1.01
    stood
    -0.79
    vironment
    -0.78
    istance
    -0.73
    ¥ŀ
    -0.68
    ossier
    -0.63
     pestic
    -0.63
    senal
    -0.62
    Rated
    -0.61
    ngth
    -0.61
    POSITIVE LOGITS
    iru
    0.71
    skip
    0.68
     [+]
    0.67
     thumbnail
    0.62
     curl
    0.62
     Birch
    0.61
     Subscribe
    0.60
     BELOW
    0.60
    asses
    0.59
    boats
    0.59
    Act Density 0.030%

    No Known Activations