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

    Neuronpedia

    INDEX
    Explanations

    references to the surname "Sanders."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -1.12
     autorytatywna
    -0.91
    IntoConstraints
    -0.89
    ConstraintMaker
    -0.87
     désolés
    -0.83
     للمعارف
    -0.83
    AxisAlignment
    -0.81
     MaterialApp
    -0.81
    Geplaatst
    -0.80
    Дереккөздер
    -0.78
    POSITIVE LOGITS
    -
    1.10
    _
    0.59
    –
    0.42
    /
    0.41
     -
    0.40
    ־
    0.39
    ,
    0.38
    1
    0.38
    ‐
    0.37
    ്
    0.37
    Act Density 0.063%

    No Known Activations