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

    Neuronpedia

    INDEX
    Explanations

    instances of the first-person pronoun "I" and related phrases expressing uncertainty or personal reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.75
    RegressionTest
    -0.66
    +:+
    -0.61
    stdafx
    -0.60
    Obrázky
    -0.54
    WithIOException
    -0.54
     nahilalakip
    -0.53
     Merah
    -0.52
     numerus
    -0.51
    jenost
    -0.51
    POSITIVE LOGITS
     desconoc
    1.50
     unknown
    1.48
     desconhe
    1.39
    unknown
    1.37
     Unknown
    1.33
     ignorance
    1.32
     unaware
    1.19
    Unknown
    1.19
     clueless
    1.18
     unknowns
    1.16
    Act Density 0.287%

    No Known Activations