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

    Neuronpedia

    INDEX
    Explanations

    references to legal or formal documents and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.52
    PerformLayout
    -0.46
    UserScript
    -0.44
     nakalista
    -0.43
    Примітки
    -0.42
     ***!
    -0.42
    Aholisi
    -0.41
    stood
    -0.40
     autorytatywna
    -0.40
     Italijanski
    -0.39
    POSITIVE LOGITS
     anymore
    0.70
     unless
    0.59
     enää
    0.58
     jemals
    0.55
     nor
    0.53
     żad
    0.51
     ninguém
    0.50
     quaisquer
    0.49
     because
    0.48
    任何人
    0.48
    Act Density 0.146%

    No Known Activations