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

    Neuronpedia

    INDEX
    Explanations

    instructions related to a user interface or software functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    òi
    -0.15
     Truy
    -0.14
    боÑĤ
    -0.14
    ĨĴ
    -0.14
    king
    -0.14
    roducing
    -0.13
    792
    -0.13
    äl
    -0.13
     fark
    -0.13
     Oscars
    -0.13
    POSITIVE LOGITS
     save
    0.47
     Save
    0.46
     saving
    0.44
    save
    0.43
     saves
    0.42
     SAVE
    0.42
    Save
    0.42
    .save
    0.40
    ä¿ĿåŃĺ
    0.40
    _save
    0.40
    Act Density 0.078%

    No Known Activations