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

    Neuronpedia

    INDEX
    Explanations

    words associated with geographical and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emie
    -0.17
    adies
    -0.16
    apor
    -0.16
    oblin
    -0.16
    ery
    -0.16
    bane
    -0.16
    omm
    -0.16
    heck
    -0.16
    ég
    -0.15
    apo
    -0.15
    POSITIVE LOGITS
    ux
    0.38
    ix
    0.31
    UX
    0.28
    uve
    0.27
    uv
    0.26
    iller
    0.25
    uil
    0.24
    indre
    0.24
    ignant
    0.24
    urs
    0.23
    Act Density 0.042%

    No Known Activations