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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific entities, locations, and classifications within diverse categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mess
    -0.15
    inka
    -0.14
    bish
    -0.14
     mey
    -0.14
     Mess
    -0.13
     Cop
    -0.13
    Ñģл
    -0.13
     bodies
    -0.13
     travel
    -0.13
     Bart
    -0.13
    POSITIVE LOGITS
     Äijá»Ŀi
    0.17
    ลา
    0.15
    okit
    0.15
    endale
    0.15
    /gtest
    0.15
    imb
    0.15
    RuleContext
    0.15
    Leaks
    0.14
    aki
    0.14
    UNDLE
    0.14
    Act Density 0.270%

    No Known Activations