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

    Neuronpedia

    INDEX
    Explanations

    references to specific model features and specifications in automotive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucu
    -0.16
    DG
    -0.15
     Virgin
    -0.14
    лам
    -0.14
    isser
    -0.14
    igin
    -0.14
    hower
    -0.14
    ente
    -0.14
    ศาสà¸ķร
    -0.14
    lore
    -0.14
    POSITIVE LOGITS
    undra
    0.17
     modest
    0.16
     somehow
    0.16
     forthcoming
    0.15
     fasc
    0.15
     expect
    0.15
     expectations
    0.15
    anja
    0.15
     new
    0.15
     expectation
    0.15
    Act Density 0.026%

    No Known Activations