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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or instructions related to software or system operations

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and actions related to software installation and setup processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulture
    -0.82
    wings
    -0.75
    é¾įå
    -0.75
    stead
    -0.75
    fell
    -0.73
    brand
    -0.73
     tragedies
    -0.72
    usterity
    -0.72
    mens
    -0.71
    uries
    -0.70
    POSITIVE LOGITS
     automatically
    1.06
     output
    1.00
     duplicate
    0.86
     milliseconds
    0.86
     ERROR
    0.83
     Output
    0.83
     cursor
    0.83
     overwrite
    0.82
     functionality
    0.82
     lookup
    0.80
    Act Density 0.397%

    No Known Activations