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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the beginning of a new section or paragraph

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     da
    -0.52
     pa
    -0.50
     Bo
    -0.50
     Tar
    -0.49
     Fa
    -0.49
     Pa
    -0.48
     Bi
    -0.48
     Ha
    -0.47
    avo
    -0.47
    audiovisuel
    -0.47
    POSITIVE LOGITS
    CA
    0.89
    IA
    0.75
     cherchés
    0.74
    CAA
    0.74
     CAA
    0.73
     occaf
    0.69
    IAA
    0.69
     Shakspeare
    0.67
     bezeichneter
    0.67
    MAA
    0.66
    Act Density 0.069%

    No Known Activations