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

    Neuronpedia

    INDEX
    Explanations

    strings of characters that contain letter combinations and numerical values, often in structured formats like figures or tables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -
    -0.66
    ,
    -0.63
     mer
    -0.61
     "
    -0.58
    ...
    -0.58
     people
    -0.57
     “
    -0.57
    .
    -0.57
     all
    -0.56
     dé
    -0.56
    POSITIVE LOGITS
    URLException
    1.08
    ConstraintMaker
    0.98
     ainfi
    0.95
    TagMode
    0.93
    ValueStyle
    0.90
    HomeAsUpEnabled
    0.88
     iſt
    0.88
     Monfieur
    0.88
    CloseOperation
    0.87
     feroit
    0.87
    Act Density 0.640%

    No Known Activations