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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political statements or actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ense
    -0.74
     orient
    -0.70
    axter
    -0.69
    brid
    -0.68
    ENTS
    -0.66
    est
    -0.66
     encount
    -0.65
    ele
    -0.64
    outheast
    -0.64
    etheless
    -0.64
    POSITIVE LOGITS
     Nope
    1.48
     Yep
    1.20
     Yeah
    1.15
     Absolutely
    1.10
     Nah
    1.10
     Probably
    1.09
     Possibly
    1.07
     Hmm
    1.01
     Yes
    1.01
     Sure
    1.00
    Act Density 0.077%

    No Known Activations