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

    Neuronpedia

    INDEX
    Explanations

    words related to medical or therapeutic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.15
    ảo
    -0.15
    PLAN
    -0.14
    erdale
    -0.14
     Pis
    -0.14
    oso
    -0.14
    ilter
    -0.14
    ilent
    -0.13
    èĻ
    -0.13
    Bindable
    -0.13
    POSITIVE LOGITS
    ziej
    0.21
    nes
    0.16
    ulp
    0.15
    lox
    0.15
    utter
    0.15
    inox
    0.14
    zion
    0.14
    ÄĻd
    0.14
    optimized
    0.14
    леÑĤ
    0.13
    Act Density 0.019%

    No Known Activations