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

    Neuronpedia

    INDEX
    Explanations

    buttons and options for selecting and clicking in interface instructions

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to user interface interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lycer
    -0.70
    bred
    -0.70
    yon
    -0.69
     Bridgewater
    -0.67
    HOU
    -0.65
    udic
    -0.64
    pron
    -0.64
     Tunis
    -0.63
    carb
    -0.62
    enz
    -0.62
    POSITIVE LOGITS
     captcha
    0.77
     Ctrl
    0.73
     "<
    0.72
     Delete
    0.71
     ENTER
    0.70
     \"
    0.69
     CTRL
    0.68
    ername
    0.68
     Submit
    0.68
     buttons
    0.67
    Act Density 0.075%

    No Known Activations