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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _gradients
    -0.15
    WISE
    -0.15
    591
    -0.15
    lfw
    -0.15
    evin
    -0.14
    emean
    -0.14
    ght
    -0.14
    atrice
    -0.14
    amedi
    -0.14
    ombine
    -0.14
    POSITIVE LOGITS
    rient
    0.16
    airo
    0.14
    era
    0.14
    ë¥ĺ
    0.14
    "https
    0.13
    اث
    0.13
    éĽ
    0.13
    nym
    0.13
    phant
    0.13
    ERA
    0.13
    Act Density 0.056%

    No Known Activations