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

    Neuronpedia

    INDEX
    Explanations

    specific quantities, levels, or significant adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     evidence
    -0.20
     legislation
    -0.18
     stuff
    -0.18
     footage
    -0.18
    ses
    -0.16
     documentation
    -0.16
    ointed
    -0.16
     progress
    -0.15
    ung
    -0.15
    ynn
    -0.15
    POSITIVE LOGITS
     Guarantee
    0.16
     probl
    0.15
    زÛĮ
    0.15
    (stdin
    0.14
    acin
    0.14
     evet
    0.14
    .infinity
    0.14
     Guar
    0.14
    ẫ
    0.14
    uras
    0.14
    Act Density 0.266%

    No Known Activations