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

    Neuronpedia

    INDEX
    Explanations

    words related to urgent matters or calls to action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    endas
    -0.80
    rex
    -0.80
    seless
    -0.69
    expensive
    -0.66
    rea
    -0.64
    itals
    -0.62
    romy
    -0.62
    pees
    -0.61
    rez
    -0.60
    ribes
    -0.60
    POSITIVE LOGITS
    THING
    1.39
    WHERE
    1.17
    body
    1.13
    where
    1.09
     conceivable
    0.96
    ONE
    0.95
     semblance
    0.91
     kind
    0.89
    thin
    0.89
    how
    0.87
    Act Density 0.344%

    No Known Activations