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

    Neuronpedia

    INDEX
    Explanations

    concepts related to artificial intelligence, machine learning, and their underlying processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.52
    hotra
    -0.48
     '
    -0.47
     
    -0.40
     посвя
    -0.39
    ;
    -0.38
    ...
    -0.38
     sup
    -0.38
     personal
    -0.37
     very
    -0.37
    POSITIVE LOGITS
    ########.
    1.10
    \{\\
    1.00
     CreateTagHelper
    1.00
     pleaſure
    0.95
     rospy
    0.94
     مرئيه
    0.93
     Roskov
    0.91
     transfieras
    0.90
    ValueStyle
    0.90
     يتيمه
    0.90
    Act Density 0.975%

    No Known Activations