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

    Neuronpedia

    INDEX
    Explanations

    words related to hierarchy and categorization, particularly in the context of relationships or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anco
    -0.18
    mlin
    -0.16
    oken
    -0.14
    /Linux
    -0.14
    alar
    -0.14
    abet
    -0.14
    okers
    -0.14
    /cat
    -0.14
    /photo
    -0.14
    ialis
    -0.13
    POSITIVE LOGITS
    wi
    0.16
    IMER
    0.15
    158
    0.15
    IEL
    0.14
    999
    0.14
    unner
    0.14
    iddleware
    0.14
    unta
    0.13
    /support
    0.13
    DMI
    0.13
    Act Density 0.395%

    No Known Activations