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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.75
    ]--;
    -0.70
     sī
    -0.55
    rxjs
    -0.55
     Barbier
    -0.54
    ussi
    -0.54
     Stolz
    -0.54
    addClass
    -0.54
     SIMBAD
    -0.53
    Controllo
    -0.53
    POSITIVE LOGITS
    новниш
    0.67
    invokeLater
    0.61
     it
    0.55
     we
    0.52
     my
    0.52
    HasForeignKey
    0.52
     wouldn
    0.50
    fficio
    0.50
    avajillas
    0.49
     they
    0.49
    Act Density 0.179%

    No Known Activations