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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical pressing or pushing

    oai_token-act-pair · gpt-3.5-turbo

    instructions or commands related to pressing buttons or controls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nown
    -0.85
    anie
    -0.75
    /-
    -0.71
    obe
    -0.67
    iatus
    -0.66
     redes
    -0.64
    vich
    -0.63
    lihood
    -0.63
    zinski
    -0.61
    aez
    -0.60
    POSITIVE LOGITS
    urized
    1.19
    ured
    0.84
    ur
    0.84
     buttons
    0.84
    ures
    0.83
    press
    0.81
     presses
    0.76
    ioned
    0.71
    agate
    0.71
    ãĥĺ
    0.70
    Act Density 0.031%

    No Known Activations