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

    Neuronpedia

    INDEX
    Explanations

    structured numerical values or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     träd
    -0.49
     puesta
    -0.43
     stort
    -0.42
    före
    -0.42
     gouvernements
    -0.40
     politiques
    -0.39
     vérit
    -0.38
     venit
    -0.38
    ↵↵
    -0.37
    ことで
    -0.37
    POSITIVE LOGITS
    AndEndTag
    0.93
     HasFactory
    0.91
     CreateTagHelper
    0.90
    ConstraintMaker
    0.87
    клопе
    0.87
    aarrggbb
    0.80
    ::$_
    0.78
    MemoryWarning
    0.77
    Билгалдахарш
    0.77
    COUVER
    0.74
    Act Density 1.072%

    No Known Activations