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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate relationships and interactions between characters or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .SDK
    -0.16
    ses
    -0.15
    ahn
    -0.14
    agua
    -0.14
    oman
    -0.14
     Mane
    -0.14
    sf
    -0.14
    анÑĥ
    -0.14
    EqualTo
    -0.13
    rado
    -0.13
    POSITIVE LOGITS
     Watkins
    0.15
    itori
    0.15
     defe
    0.15
    StringRef
    0.15
    iras
    0.14
    oola
    0.14
    ienes
    0.14
    é»İ
    0.14
    roi
    0.14
    roys
    0.14
    Act Density 0.312%

    No Known Activations