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

    Neuronpedia

    INDEX
    Explanations

    references to protective barriers or defenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elles
    -0.18
    lish
    -0.15
    PasswordField
    -0.15
    yonel
    -0.15
    ìĶ
    -0.14
    íĴĪ
    -0.14
    elsing
    -0.14
    arkin
    -0.14
    λλην
    -0.14
    eled
    -0.14
    POSITIVE LOGITS
     Cliff
    0.16
    unders
    0.15
     vi
    0.15
    .usermodel
    0.14
    nu
    0.14
    avn
    0.14
    idine
    0.14
    izu
    0.14
    vari
    0.14
    ab
    0.14
    Act Density 0.006%

    No Known Activations