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

    Neuronpedia

    INDEX
    Explanations

    words related to investigations and inquiries

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TA
    -0.78
    yip
    -0.75
     ancest
    -0.68
    Chart
    -0.66
    anguage
    -0.65
    oire
    -0.63
     ported
    -0.63
    reference
    -0.62
     rejoice
    -0.62
    inline
    -0.62
    POSITIVE LOGITS
     whether
    0.87
     Integrity
    0.81
     allegations
    0.77
     misconduct
    0.75
     wrongdoing
    0.73
     alleged
    0.72
     probing
    0.71
     Journalism
    0.71
     UFOs
    0.71
     Scientology
    0.70
    Act Density 0.036%

    No Known Activations