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

    Neuronpedia

    INDEX
    Explanations

    references to academic reports and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    COPE
    -0.17
    lotte
    -0.16
     Motion
    -0.15
    hl
    -0.15
    Motion
    -0.15
    nda
    -0.14
     discharge
    -0.14
    füh
    -0.14
    alis
    -0.14
    upo
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.21
     Seeder
    0.17
     Seah
    0.15
    .crm
    0.15
    ewood
    0.15
    occan
    0.15
    RTOS
    0.14
    %X
    0.14
    iami
    0.14
     pure
    0.13
    Act Density 0.010%

    No Known Activations