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

    Neuronpedia

    INDEX
    Explanations

    words related to political events and actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     imperfect
    -0.72
     americ
    -0.69
    Reviewer
    -0.68
     eccentric
    -0.68
     felon
    -0.67
     neutrality
    -0.67
     annoyance
    -0.66
     surn
    -0.66
     spoilers
    -0.66
     impulse
    -0.66
    POSITIVE LOGITS
    ighed
    1.39
    uates
    1.23
    ating
    1.15
    uated
    1.15
    ved
    1.15
    istered
    1.14
    uating
    1.14
    ated
    1.14
    icating
    1.14
    ussed
    1.14
    Act Density 0.250%

    No Known Activations