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

    Neuronpedia

    INDEX
    Explanations

    references to academic journal volumes and issue numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utow
    -0.17
    ettel
    -0.16
    uppen
    -0.15
    rex
    -0.15
    allas
    -0.15
     cast
    -0.15
    iaz
    -0.14
    utin
    -0.14
    uide
    -0.14
    orning
    -0.14
    POSITIVE LOGITS
    alama
    0.16
     Sher
    0.15
    Sher
    0.15
    enburg
    0.14
    ocos
    0.14
    /raw
    0.14
    /rc
    0.14
    Advisor
    0.13
    .navigator
    0.13
     ì²
    0.13
    Act Density 0.005%

    No Known Activations