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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases that indicate a conclusion or explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RENDER
    -0.54
    Afin
    -0.50
     typelib
    -0.49
     Geister
    -0.48
     onBind
    -0.48
     знал
    -0.47
    достатки
    -0.47
     данной
    -0.47
    ATURA
    -0.47
    FromNib
    -0.46
    POSITIVE LOGITS
     это
    2.70
     Это
    2.14
    Это
    1.95
    это
    1.91
     це
    1.61
     eso
    1.32
     isso
    1.25
     Це
    1.22
    それは
    1.21
    Це
    1.14
    Act Density 0.043%

    No Known Activations