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

    Neuronpedia

    INDEX
    Explanations

    concepts related to judgment and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alyze
    -0.16
    quisition
    -0.15
    ignment
    -0.15
    uality
    -0.14
    mination
    -0.14
    enade
    -0.14
    Ĥ¬
    -0.14
     â
    -0.13
     sund
    -0.13
    appable
    -0.13
    POSITIVE LOGITS
    etheless
    0.20
     же
    0.19
    prisingly
    0.19
    umably
    0.18
    uably
    0.18
    ingly
    0.18
    arently
    0.17
    oubtedly
    0.17
    sequently
    0.17
    -wise
    0.17
    Act Density 0.217%

    No Known Activations