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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or limitations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     until
    -0.82
     unless
    -0.79
    until
    -0.79
    unless
    -0.79
    Until
    -0.76
     UNTIL
    -0.74
     Until
    -0.73
     Unless
    -0.70
     untill
    -0.70
     till
    -0.69
    POSITIVE LOGITS
     AssemblyCulture
    1.23
     Normdatei
    0.97
     الرياضيه
    0.91
     GenerationType
    0.90
    featureID
    0.88
    TagMode
    0.87
    Geplaatst
    0.85
    الإنجليزية
    0.84
    脚注の使い方
    0.84
    StoryboardSegue
    0.83
    Act Density 0.015%

    No Known Activations