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

    Neuronpedia

    INDEX
    Explanations

    statements about societal issues and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umber
    -0.16
     Autodesk
    -0.15
    ortex
    -0.15
    zig
    -0.15
    ÐĴС
    -0.14
    umberland
    -0.14
    ÑĤак
    -0.14
    emi
    -0.14
    åĢī
    -0.14
    unist
    -0.14
    POSITIVE LOGITS
     Operation
    0.23
     Tian
    0.23
     Locker
    0.23
     Tray
    0.23
     Challenger
    0.20
     Pearl
    0.20
     Desert
    0.20
     Colum
    0.20
     September
    0.20
     Sandy
    0.19
    Act Density 0.389%

    No Known Activations