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

    Neuronpedia

    INDEX
    Explanations

    the word "Kon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ece
    -0.20
    ylon
    -0.17
    quo
    -0.17
    eous
    -0.17
    yth
    -0.17
    e
    -0.16
    eut
    -0.16
    ei
    -0.16
    eing
    -0.16
    eah
    -0.16
    POSITIVE LOGITS
    stant
    0.29
    rad
    0.25
    igs
    0.24
    stan
    0.21
    kre
    0.21
    cert
    0.20
    trap
    0.20
    راد
    0.19
    ÏĥÏĦαν
    0.19
    f
    0.19
    Act Density 0.009%

    No Known Activations