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

    Neuronpedia

    INDEX
    Explanations

    words related to administrative or bureaucratic actions and designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istine
    -0.15
    ÙĪÙĦÙĩ
    -0.15
    ë¡Ŀ
    -0.15
    <typeof
    -0.15
    odem
    -0.15
    isify
    -0.15
    intage
    -0.14
    견
    -0.14
    \Modules
    -0.14
    ìŀĶ
    -0.14
    POSITIVE LOGITS
    ill
    0.18
    ert
    0.15
    ro
    0.15
     Hussein
    0.14
    orry
    0.14
    rant
    0.14
    enstein
    0.14
    atz
    0.14
    chin
    0.14
    much
    0.13
    Act Density 0.073%

    No Known Activations