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

    Neuronpedia

    INDEX
    Explanations

    references to GitHub and the concept of neutrality in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.61
    Portale
    -0.61
     lyder
    -0.54
    획
    -0.52
     Board
    -0.52
     Marlon
    -0.52
     <<<<<<<<<<<<<<
    -0.52
     Possession
    -0.52
     Sirs
    -0.51
     FIFO
    -0.51
    POSITIVE LOGITS
     neutral
    1.21
     Neutral
    1.10
    neutral
    1.06
    Neutral
    1.04
     нейтра
    0.82
    UTRAL
    0.82
     neutrals
    0.79
    т
    0.79
     cancel
    0.78
     neutrality
    0.78
    Act Density 0.089%

    No Known Activations