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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief or conviction related to values or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ez
    -0.17
    ependency
    -0.16
    esthes
    -0.14
    efe
    -0.14
    ebin
    -0.14
    ammable
    -0.14
    oke
    -0.14
    ertino
    -0.14
    eldo
    -0.14
    ecycle
    -0.14
    POSITIVE LOGITS
    ance
    0.17
    distributed
    0.14
    ansı
    0.14
     infra
    0.13
     magic
    0.13
    magic
    0.13
    borough
    0.13
    Forge
    0.13
    n
    0.13
    dÄĽ
    0.13
    Act Density 0.056%

    No Known Activations