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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to proof and verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unch
    -0.17
    ê»ĺ
    -0.15
    oral
    -0.15
    vre
    -0.15
    gi
    -0.15
    lle
    -0.15
    ÑĥÑģ
    -0.15
    arium
    -0.14
    -gnu
    -0.14
    ised
    -0.14
    POSITIVE LOGITS
    reading
    0.25
    lessly
    0.17
    /dis
    0.16
    edores
    0.16
     pudding
    0.15
    duc
    0.15
    íıIJ
    0.15
    reader
    0.15
    read
    0.15
    ought
    0.15
    Act Density 0.022%

    No Known Activations