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

    Neuronpedia

    INDEX
    Explanations

    assertions and statements of fact in scientific or analytical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quels
    -0.83
     quien
    -0.66
    Which
    -0.61
    who
    -0.60
     relâche
    -0.59
    this
    -0.59
    quien
    -0.59
    OfThe
    -0.59
    quelles
    -0.59
    Such
    -0.57
    POSITIVE LOGITS
     that
    3.53
     bahwa
    1.54
    that
    1.37
     rằng
    1.27
     że
    1.18
     dass
    1.17
     bahawa
    1.14
     که
    1.13
     kwamba
    1.11
     että
    1.10
    Act Density 3.038%

    No Known Activations