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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions indicating confusion or uncertainty

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.98
     Monfieur
    -0.92
     Jefus
    -0.91
     فريبيس
    -0.90
    rainian
    -0.89
     AssemblyCulture
    -0.87
     themſelves
    -0.87
     Majefty
    -0.84
     myſelf
    -0.84
     Efq
    -0.83
    POSITIVE LOGITS
     Mar
    0.58
    ↵↵
    0.54
     may
    0.52
     Al
    0.52
     Y
    0.50
     I
    0.49
     Thus
    0.49
     Ber
    0.48
     Her
    0.48
     P
    0.48
    Act Density 0.077%

    No Known Activations