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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.98
     Monfieur
    -0.86
     Chriftian
    -0.84
     itſelf
    -0.82
     habet
    -0.82
     fubject
    -0.82
     purpoſe
    -0.82
     raiſ
    -0.81
    aarrggbb
    -0.81
    IntoConstraints
    -0.81
    POSITIVE LOGITS
     f
    0.51
     O
    0.49
     o
    0.47
     ur
    0.47
    ↵↵
    0.46
     III
    0.46
     U
    0.44
     tor
    0.44
     II
    0.43
    lers
    0.43
    Act Density 1.734%

    No Known Activations