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

    Neuronpedia

    INDEX
    Explanations

    negative statements and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.16
    足
    -0.15
     McMahon
    -0.15
    ãĤ¦ãĥ³
    -0.15
    _Inter
    -0.15
    kip
    -0.15
    nds
    -0.14
    ÑĴ
    -0.14
    ApplicationBuilder
    -0.14
    LObject
    -0.14
    POSITIVE LOGITS
     gross
    0.17
     buck
    0.16
    awai
    0.15
     vice
    0.14
    roke
    0.14
    èĨ
    0.14
     sinking
    0.13
    gross
    0.13
     el
    0.13
     Brad
    0.13
    Act Density 0.001%

    No Known Activations