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

    Neuronpedia

    INDEX
    Explanations

    words related to standardization or typical characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ра
    -0.68
    landı
    -0.60
    anu
    -0.60
    åde
    -0.58
    gun
    -0.57
    ぐり
    -0.56
     bin
    -0.55
    Kund
    -0.55
    ResponseEntity
    -0.55
    Ker
    -0.55
    POSITIVE LOGITS
     typical
    2.70
    typical
    2.67
    Typical
    2.57
     Typical
    2.55
     typique
    2.07
     típico
    1.96
     TYP
    1.88
     típica
    1.85
    典型的
    1.79
     típicos
    1.75
    Act Density 0.050%

    No Known Activations