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

    Neuronpedia

    INDEX
    Explanations

    terms related to enhancement or improvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hood
    -0.19
    NESS
    -0.17
    claimer
    -0.16
    nd
    -0.15
    fully
    -0.15
    -eyed
    -0.15
    bones
    -0.15
    dust
    -0.15
    elsius
    -0.14
    InstanceOf
    -0.14
    POSITIVE LOGITS
    /de
    0.19
    /disable
    0.18
    akit
    0.18
    åIJİçļĦ
    0.17
    akov
    0.17
    okit
    0.16
    ments
    0.16
    yth
    0.16
     opportunities
    0.15
    /en
    0.15
    Act Density 0.032%

    No Known Activations