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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structural markers in textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ねて
    -0.59
     Einfluß
    -0.56
    Jereo
    -0.56
    mberg
    -0.53
     utafitiHapana
    -0.52
    …
    -0.51
    Cyfeiriadau
    -0.50
    ongen
    -0.50
    ləş
    -0.49
    ########.
    -0.49
    POSITIVE LOGITS
    complexContent
    0.67
     perdon
    0.58
     cherchés
    0.57
    ⓧ
    0.57
    mögens
    0.55
    Personendaten
    0.55
    Naissance
    0.55
    RegistryLite
    0.55
    sprozess
    0.54
    })*/
    0.52
    Act Density 0.029%

    No Known Activations