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

    Neuronpedia

    INDEX
    Explanations

    gender differences and their effects in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.98
     فريبيس
    -0.97
     itſelf
    -0.84
    Personensuche
    -0.82
    CppMethod
    -0.78
     myſelf
    -0.76
    GEBURTSDATUM
    -0.74
    EndGlobalSection
    -0.73
     Jefus
    -0.73
     Theſe
    -0.71
    POSITIVE LOGITS
    enumi
    0.46
    velocityX
    0.42
    imai
    0.41
     them
    0.40
     >
    0.40
     henne
    0.38
     kema
    0.37
    fetchone
    0.37
     répertoire
    0.37
     or
    0.36
    Act Density 0.257%

    No Known Activations