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

    Neuronpedia

    INDEX
    Explanations

    negative statements or negations in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.77
    CodeAttribute
    -0.69
    InlineData
    -0.69
     aimable
    -0.68
     émotion
    -0.66
     topl
    -0.65
     ouverture
    -0.64
    spesies
    -0.64
     lush
    -0.64
     avoient
    -0.63
    POSITIVE LOGITS
    )$_
    1.05
    '")
    0.97
    '])
    0.94
    '):
    0.92
    '),
    0.91
    '))
    0.90
    ')"
    0.87
    '},
    0.86
    ')],
    0.86
    "]),
    0.85
    Act Density 0.030%

    No Known Activations