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

    Neuronpedia

    INDEX
    Explanations

    elements that represent structured data or lists in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cken
    -0.17
    egend
    -0.17
    ÏĥÏĩ
    -0.17
    jug
    -0.16
    eder
    -0.16
    pent
    -0.16
    idot
    -0.15
    éĻµ
    -0.15
    idon
    -0.14
    aga
    -0.14
    POSITIVE LOGITS
     INTERVAL
    0.15
    opia
    0.15
    worth
    0.15
    uml
    0.14
     Culture
    0.14
    Zone
    0.14
    zos
    0.14
    ledi
    0.14
    çłĶ究æīĢ
    0.13
    jit
    0.13
    Act Density 0.017%

    No Known Activations