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

    Neuronpedia

    INDEX
    Explanations

    first-person expressions of self-awareness and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pliny
    -0.83
     Allegretto
    -0.75
     Jefus
    -0.72
    Попис
    -0.71
    RectangleBorder
    -0.70
     wanna
    -0.69
    }}^{(
    -0.68
     Schot
    -0.67
     Juf
    -0.66
    ýš
    -0.65
    POSITIVE LOGITS
     تضيفلها
    0.74
     Osborne
    0.73
     ApiResponse
    0.72
     läßt
    0.72
    Ці
    0.72
     destes
    0.70
    writeFieldEnd
    0.69
    complexContent
    0.69
     paesi
    0.69
     يتيمه
    0.68
    Act Density 0.437%

    No Known Activations