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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data access and user control

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DockStyle
    -1.07
     Efq
    -0.93
     Majefty
    -0.90
    StoryboardSegue
    -0.88
    aarrggbb
    -0.85
     '\\;'
    -0.84
     Monfieur
    -0.83
     cherchés
    -0.79
    hasMoreElements
    -0.79
    IntoConstraints
    -0.79
    POSITIVE LOGITS
     Sign
    0.47
     fil
    0.46
    Sign
    0.44
     ات
    0.42
     –
    0.42
     regola
    0.40
    迫
    0.40
     lệ
    0.40
     Einwilligung
    0.40
     e
    0.40
    Act Density 0.015%

    No Known Activations