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

    Neuronpedia

    INDEX
    Explanations

    instances of underscores in varying frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.86
    '},
    -0.86
    #+#
    -0.84
    OGND
    -0.81
     ivelany
    -0.80
    ="#"><
    -0.78
    niająca
    -0.75
    TagMode
    -0.74
    ?<
    -0.74
     NavController
    -0.74
    POSITIVE LOGITS
    __
    2.74
    .__
    0.85
    \_\_
    0.77
    ___
    0.74
    __'
    0.68
     __
    0.65
    --
    0.64
    ____
    0.59
    '__
    0.57
    __',
    0.54
    Act Density 0.094%

    No Known Activations