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

    Neuronpedia

    INDEX
    Explanations

    references to software package structures and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tru
    -0.17
    986
    -0.16
    loh
    -0.15
    exus
    -0.15
    eries
    -0.15
    oulos
    -0.14
    inja
    -0.14
    rex
    -0.14
    anou
    -0.14
     constr
    -0.14
    POSITIVE LOGITS
    azer
    0.15
    urai
    0.15
     Transfer
    0.15
    abus
    0.14
     Rab
    0.14
    evice
    0.14
     addCriterion
    0.14
    owski
    0.14
    EOF
    0.14
    _altern
    0.14
    Act Density 0.008%

    No Known Activations