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

    Neuronpedia

    INDEX
    Explanations

    references to superstitions, supernatural beliefs, and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to superstition and the supernatural

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    cule
    -0.68
    den
    -0.66
    bian
    -0.66
    stretched
    -0.64
     Gleaming
    -0.63
    stan
    -0.61
    nin
    -0.61
    anian
    -0.61
    ting
    -0.59
    POSITIVE LOGITS
    itious
    1.14
    ition
    1.08
    ructure
    1.03
    ific
    1.02
    itions
    0.97
    atural
    0.84
    izers
    0.83
    inct
    0.82
    ormal
    0.81
    izations
    0.81
    Act Density 0.055%

    No Known Activations