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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social commentary or criticism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uum
    -0.69
     Airl
    -0.68
    ributed
    -0.68
    ascript
    -0.67
    icidal
    -0.66
    ieu
    -0.65
    eyed
    -0.65
    imb
    -0.63
     Institution
    -0.61
    ashed
    -0.61
    POSITIVE LOGITS
    adays
    1.40
    here
    0.96
     belongs
    0.79
     comes
    0.73
    nir
    0.73
     confronts
    0.72
     resides
    0.71
     defunct
    0.71
     behold
    0.71
     awaits
    0.70
    Act Density 0.049%

    No Known Activations