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

    Neuronpedia

    INDEX
    Explanations

    terms related to upgrades and improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xia
    -0.16
    stalk
    -0.16
    rer
    -0.15
    /me
    -0.14
    ULA
    -0.14
    alice
    -0.14
    uckle
    -0.14
    ource
    -0.13
    arty
    -0.13
    sey
    -0.13
    POSITIVE LOGITS
    'gc
    0.19
    /down
    0.17
     dần
    0.16
    InputDialog
    0.15
    ạc
    0.15
    /extensions
    0.14
    ίο
    0.14
    alama
    0.14
    ritch
    0.14
    endas
    0.14
    Act Density 0.013%

    No Known Activations