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

    Neuronpedia

    INDEX
    Explanations

    statements expressing opinions or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⇀
    -0.39
     rhiz
    -0.39
    盲
    -0.38
    kuma
    -0.38
    präche
    -0.37
     direct
    -0.36
     Direct
    -0.34
     LESS
    -0.33
     gos
    -0.33
     النه
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.69
    styleType
    0.56
    grà
    0.52
    hoeddwyd
    0.52
    Personendaten
    0.49
    verwijspagina
    0.46
     دیکھیے
    0.46
    相关文章
    0.46
     onOptions
    0.46
    ंदीखरीदारी
    0.45
    Act Density 0.850%

    No Known Activations