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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to hardware and its usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìķ¼
    -0.25
     hence
    -0.23
     Hence
    -0.23
     holistic
    -0.20
     harsh
    -0.19
     hypothetical
    -0.17
     highly
    -0.17
    /he
    -0.17
     unh
    -0.17
    _hierarchy
    -0.17
    POSITIVE LOGITS
    RowAtIndexPath
    0.23
    iday
    0.23
    sworth
    0.22
    izons
    0.21
    forth
    0.21
    ERSHEY
    0.21
    /software
    0.21
     sapi
    0.20
    archical
    0.18
    ilities
    0.18
    Act Density 1.114%

    No Known Activations