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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating composition or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caught
    -0.15
    jong
    -0.15
    ghan
    -0.15
    ãng
    -0.15
    ÑĪи
    -0.15
    jÃł
    -0.15
    çIJĨçĶ±
    -0.15
    iens
    -0.14
    atal
    -0.14
    jan
    -0.14
    POSITIVE LOGITS
     of
    0.18
     adm
    0.18
    ointments
    0.16
    ůj
    0.16
     elements
    0.15
     components
    0.15
     halinde
    0.15
    æĶ
    0.15
     entirely
    0.15
    cons
    0.15
    Act Density 0.030%

    No Known Activations