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

    Neuronpedia

    INDEX
    Explanations

    references to a specific entity or organization, specifically those that start with "Kon" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eon
    -0.21
    eel
    -0.18
    eum
    -0.17
    dana
    -0.17
    avana
    -0.16
    eled
    -0.16
    eous
    -0.16
    ois
    -0.16
    ece
    -0.16
    uteur
    -0.16
    POSITIVE LOGITS
    igs
    0.21
    stant
    0.21
    rad
    0.20
    ig
    0.18
    ishi
    0.18
    ÏĥÏĦαν
    0.18
    ardy
    0.18
    ings
    0.17
    jac
    0.16
     tim
    0.15
    Act Density 0.010%

    No Known Activations