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

    Neuronpedia

    INDEX
    Explanations

    phrases related to allegations of misconduct and controversy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fluo
    -0.97
     thermomix
    -0.95
     ampoule
    -0.93
     oleo
    -0.81
     clayey
    -0.79
     swarovski
    -0.78
     embodi
    -0.78
     fusible
    -0.77
     pandan
    -0.75
     nutella
    -0.75
    POSITIVE LOGITS
     allegations
    0.79
     alleged
    0.67
     allegation
    0.66
     accusations
    0.66
     alleging
    0.60
     sexual
    0.59
     Muhamma
    0.57
     scandals
    0.57
     alleges
    0.56
     revelations
    0.54
    Act Density 0.499%

    No Known Activations