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

    Neuronpedia

    INDEX
    Explanations

    words indicating the act of removal or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ходи
    -0.58
     humaines
    -0.53
     mourut
    -0.51
     приходи
    -0.50
    illoma
    -0.50
    ;
    -0.50
     âgées
    -0.49
    ತ
    -0.47
     andare
    -0.47
    piac
    -0.46
    POSITIVE LOGITS
     ***!
    0.88
    []
    0.87
    Rüyada
    0.86
     the
    0.81
    +
    0.79
    клопе
    0.78
    ]>=
    0.78
     "..\..\..\
    0.77
    AndEndTag
    0.77
     ]
    0.77
    Act Density 0.158%

    No Known Activations