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

    Neuronpedia

    INDEX
    Explanations

    negations or words expressing denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.84
     Roskov
    -0.64
     Мексичка
    -0.62
     suivantes
    -0.60
     terakhir
    -0.60
    the
    -0.57
     cref
    -0.54
     betweenstory
    -0.51
     számára
    -0.50
     tertinggi
    -0.50
    POSITIVE LOGITS
     matter
    1.45
     amount
    1.11
     doubt
    0.97
     longer
    0.90
    tably
    0.90
    bodies
    0.88
     sooner
    0.88
    BODY
    0.86
     MATTER
    0.81
     wonder
    0.80
    Act Density 0.108%

    No Known Activations