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

    Neuronpedia

    INDEX
    Explanations

    words related to movement or change

    oai_token-act-pair · gpt-3.5-turbo

    continuous action verbs and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paying
    -0.88
    aligned
    -0.88
    vised
    -0.85
    thodox
    -0.82
    zynski
    -0.79
    chery
    -0.79
    saf
    -0.79
    hers
    -0.78
    ternity
    -0.78
    correct
    -0.77
    POSITIVE LOGITS
     sands
    0.96
     tide
    0.89
     corpse
    0.83
     sun
    0.82
     jaws
    0.79
     sensation
    0.78
     Archdemon
    0.78
     hearts
    0.78
     wreckage
    0.78
     sea
    0.77
    Act Density 0.158%

    No Known Activations