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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions to perform actions on a computer interface

    oai_token-act-pair · gpt-3.5-turbo

    instructions involving user actions, particularly selecting and clicking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egal
    -0.73
    lycer
    -0.69
    emale
    -0.69
    bred
    -0.68
    jri
    -0.66
    anmar
    -0.65
    arters
    -0.65
    enz
    -0.63
     twins
    -0.61
    itters
    -0.60
    POSITIVE LOGITS
     Delete
    0.80
     Save
    0.74
     "<
    0.74
     Export
    0.73
     Ctrl
    0.73
     Apply
    0.73
    »Ĵ
    0.72
     Import
    0.71
    Save
    0.71
     Preferences
    0.69
    Act Density 0.084%

    No Known Activations