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

    Neuronpedia

    INDEX
    Explanations

    phrases related to admitting or confessing to something

    oai_token-act-pair · gpt-3.5-turbo

    instances of admissions or confessions related to various actions or crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Liber
    -0.78
    DragonMagazine
    -0.75
     Mehran
    -0.73
    reshold
    -0.73
    intosh
    -0.70
    atos
    -0.69
    Welcome
    -0.69
    eous
    -0.69
    cair
    -0.69
    soon
    -0.68
    POSITIVE LOGITS
     having
    1.21
     raping
    1.19
     wrongdoing
    1.19
     committing
    1.17
     possessing
    1.17
     owning
    1.15
     murdering
    1.12
     assaulting
    1.11
     abusing
    1.11
     manipulating
    1.11
    Act Density 0.104%

    No Known Activations