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

    Neuronpedia

    INDEX
    Explanations

    references to posters or poster-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    men
    -0.16
    emen
    -0.16
    sc
    -0.15
    /goto
    -0.15
    reich
    -0.15
    sg
    -0.15
    vil
    -0.15
    son
    -0.14
    RuntimeObject
    -0.14
    ìĶ
    -0.14
    POSITIVE LOGITS
    ised
    0.18
    ifu
    0.17
    ized
    0.17
    ry
    0.17
    ibbon
    0.17
    izes
    0.16
    iface
    0.16
    iff
    0.15
    anguages
    0.14
    efd
    0.14
    Act Density 0.049%

    No Known Activations