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

    Neuronpedia

    INDEX
    Explanations

    buttons or button-related actions

    oai_token-act-pair · gpt-3.5-turbo

    references to buttons and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.83
    ctuary
    -0.78
    ILY
    -0.74
    ews
    -0.74
     Atmosp
    -0.71
     Continuing
    -0.71
    abama
    -0.70
    yon
    -0.68
    vironment
    -0.68
    QUIRE
    -0.68
    POSITIVE LOGITS
     button
    0.92
    button
    0.91
    holes
    0.87
    hole
    0.86
     pus
    0.85
     buttons
    0.83
    btn
    0.83
    oola
    0.82
     widget
    0.79
    bell
    0.78
    Act Density 0.014%

    No Known Activations