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

    Neuronpedia

    INDEX
    Explanations

    the abbreviation "HT" associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flam
    -0.17
    ander
    -0.16
    oras
    -0.16
    ullet
    -0.15
     Base
    -0.15
    ato
    -0.14
    ipp
    -0.14
    ãģ£ãģ¨
    -0.14
    udad
    -0.14
     count
    -0.14
    POSITIVE LOGITS
    lh
    0.14
    serrat
    0.14
    bars
    0.14
    uze
    0.14
    chef
    0.14
    success
    0.14
     BindingFlags
    0.14
    оба
    0.14
    yre
    0.13
    sel
    0.13
    Act Density 0.007%

    No Known Activations