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

    Neuronpedia

    INDEX
    Explanations

    references to subsequent sections in a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     later
    -0.58
     majd
    -0.50
     originally
    -0.46
     original
    -0.46
     senere
    -0.45
    origine
    -0.44
     earlier
    -0.44
     póź
    -0.43
     pozdě
    -0.43
    veja
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    1.06
    Personendaten
    1.06
     betweenstory
    1.02
    0.98
     препратки
    0.87
    expandindo
    0.80
     виправивши
    0.77
     pinulongan
    0.76
    Portail
    0.75
     estimés
    0.75
    Act Density 0.016%

    No Known Activations