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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers and terms indicating limitations or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oneofs
    -0.76
    MENAFN
    -0.74
    tersebut
    -0.73
    ectoria
    -0.68
    ergies
    -0.68
     Jefus
    -0.68
     kasarigan
    -0.66
     Majefty
    -0.65
    endwhile
    -0.65
     themſelves
    -0.65
    POSITIVE LOGITS
     even
    0.62
     rather
    0.59
     quite
    0.58
     certainly
    0.54
     only
    0.52
     without
    0.51
     wireType
    0.51
    ม้
    0.49
    Vorlage
    0.49
     somewhat
    0.49
    Act Density 2.090%

    No Known Activations