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

    Neuronpedia

    INDEX
    Explanations

    references to sexual misconduct or related accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yne
    -0.15
     Patty
    -0.15
     minister
    -0.15
    otty
    -0.14
    ovit
    -0.14
     Rab
    -0.13
     hale
    -0.13
     sue
    -0.13
     hypo
    -0.13
    atsapp
    -0.13
    POSITIVE LOGITS
     sentencing
    0.25
     Recorder
    0.24
     sentence
    0.23
     Sentence
    0.22
     crown
    0.20
    Sentence
    0.20
    Recorder
    0.19
     sentences
    0.19
     sentenced
    0.18
     Crown
    0.18
    Act Density 0.027%

    No Known Activations