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

    Neuronpedia

    INDEX
    Explanations

    results and findings in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.78
    IntoConstraints
    -0.78
     beginnetje
    -0.75
     المعيارى
    -0.73
    PreferredItem
    -0.70
    principalTable
    -0.68
    ⓧ
    -0.68
    السكان
    -0.68
     censiti
    -0.67
     typelib
    -0.67
    POSITIVE LOGITS
     suggesting
    1.00
     suggest
    0.99
     supports
    0.97
     support
    0.95
     suggests
    0.93
     Suggest
    0.85
     Support
    0.85
    suggest
    0.83
    Support
    0.83
     SUPPORT
    0.81
    Act Density 1.570%

    No Known Activations