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

    Neuronpedia

    INDEX
    Explanations

    words related to buttons or similar physical input mechanisms

    oai_token-act-pair · gpt-3.5-turbo

    references to buttons and button-related interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctuary
    -0.84
     Flavoring
    -0.76
    ILY
    -0.73
    nces
    -0.73
     Atmosp
    -0.71
    abama
    -0.68
     Continuing
    -0.68
    spect
    -0.67
    ateur
    -0.67
    yon
    -0.66
    POSITIVE LOGITS
    holes
    1.05
    hole
    1.03
     pus
    0.94
    button
    0.85
    bell
    0.84
    nuts
    0.83
    wheel
    0.78
    btn
    0.78
     button
    0.77
    nut
    0.76
    Act Density 0.028%

    No Known Activations