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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of doubt or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.68
    ()].
    -0.67
    psack
    -0.64
    ?')
    -0.62
    };*/
    -0.62
    ']}
    -0.62
    queryInterface
    -0.60
    '));
    -0.60
    __).
    -0.58
     '
    -0.57
    POSITIVE LOGITS
    Nope
    0.64
     Nope
    0.64
    nope
    0.63
    Nein
    0.63
    errHandler
    0.62
     físicos
    0.59
     nope
    0.59
     fédéral
    0.55
    🙅
    0.55
     NSCoder
    0.54
    Act Density 0.123%

    No Known Activations