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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numeric values and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.21
    ̧
    -0.14
    es
    -0.14
    S
    -0.14
    addock
    -0.14
    angelog
    -0.14
    ifton
    -0.14
    chant
    -0.13
    eson
    -0.13
    rol
    -0.13
    POSITIVE LOGITS
    enko
    0.19
    ever
    0.14
    atik
    0.14
    kol
    0.13
    .instances
    0.13
    enticator
    0.13
    odore
    0.13
    utan
    0.13
    @brief
    0.13
    æĮĻ
    0.13
    Act Density 0.061%

    No Known Activations