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

    Neuronpedia

    INDEX
    Explanations

    references to buttons or button-related actions

    oai_token-act-pair · gpt-3.5-turbo

    references to buttons and button-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctuary
    -0.70
     Atmosp
    -0.65
     Flavoring
    -0.64
    namese
    -0.63
    nces
    -0.62
     Heller
    -0.61
     Stru
    -0.60
     Folk
    -0.60
    ILY
    -0.60
    yon
    -0.60
    POSITIVE LOGITS
    hole
    1.03
    holes
    1.02
     pus
    0.92
    button
    0.89
    nuts
    0.88
     clicked
    0.85
    btn
    0.84
    bell
    0.84
     button
    0.82
     buttons
    0.81
    Act Density 0.051%

    No Known Activations