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

    Neuronpedia

    INDEX
    Explanations

    references to essays in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mühe
    -0.40
    jenigen
    -0.37
    />,
    -0.36
    >--}}
    -0.35
     otomatig
    -0.35
    ])).
    -0.35
     Italij
    -0.34
    évaluateur
    -0.33
    ĵo
    -0.33
    今
    -0.32
    POSITIVE LOGITS
    Hentet
    0.73
    PositiveButton
    0.68
     defeats
    0.64
    CppMethod
    0.63
     defeated
    0.63
    ReusableCell
    0.62
    defe
    0.60
    ConstraintMaker
    0.59
    Btn
    0.59
    CloseOperation
    0.58
    Act Density 0.303%

    No Known Activations