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

    Neuronpedia

    INDEX
    Explanations

    insults and controversial statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ail
    -0.78
    negie
    -0.75
    ills
    -0.75
    illon
    -0.74
    frames
    -0.72
    olutions
    -0.70
    angler
    -0.67
    overs
    -0.64
    hare
    -0.64
    wings
    -0.64
    POSITIVE LOGITS
     insult
    1.07
     insulted
    1.06
     disrespect
    1.03
     slurs
    0.99
     humour
    0.93
     insulting
    0.93
     insults
    0.90
     stereotypes
    0.88
     dispar
    0.86
     humor
    0.86
    Act Density 0.071%

    No Known Activations