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

    Neuronpedia

    INDEX
    Explanations

    words related to buttons or button-like objects

    oai_token-act-pair · gpt-3.5-turbo

    references to buttons and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctuary
    -0.85
     Atmosp
    -0.77
     Flavoring
    -0.77
    ILY
    -0.77
    ews
    -0.69
     Continuing
    -0.68
    QUIRE
    -0.67
    nces
    -0.67
    ivia
    -0.67
    vironment
    -0.66
    POSITIVE LOGITS
    hole
    0.97
    holes
    0.95
     pus
    0.90
    button
    0.89
    btn
    0.83
    bell
    0.83
     button
    0.82
    oola
    0.78
    wheel
    0.74
     popup
    0.73
    Act Density 0.017%

    No Known Activations