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

    Neuronpedia

    INDEX
    Explanations

    references to specific data structures and operations within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steen
    -0.17
    went
    -0.16
    ivas
    -0.15
    olars
    -0.15
    iw
    -0.14
    aura
    -0.14
    arris
    -0.14
    csi
    -0.14
    ÏĢα
    -0.14
    icensed
    -0.13
    POSITIVE LOGITS
    ìĨĶ
    0.14
    39
    0.14
     Rav
    0.14
    rey
    0.14
    grav
    0.13
    kening
    0.13
    ext
    0.13
    _UNS
    0.13
    ryption
    0.12
     MC
    0.12
    Act Density 0.108%

    No Known Activations