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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    negative concepts related to software or technical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gallup
    -0.86
     Norris
    -0.72
     Moreno
    -0.71
     Phelps
    -0.70
     Maher
    -0.69
     Cassidy
    -0.69
     Lowry
    -0.69
     marches
    -0.68
     Carly
    -0.68
     Pett
    -0.67
    POSITIVE LOGITS
    compatible
    1.22
    mode
    1.14
    level
    1.12
    package
    1.11
    based
    1.11
    generic
    1.10
    cache
    1.09
    setup
    1.08
    spec
    1.04
    layout
    1.04
    Act Density 0.133%

    No Known Activations