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

    Neuronpedia

    INDEX
    Explanations

    negative adjectives related to immoral or unethical behavior

    oai_token-act-pair · gpt-3.5-turbo

    words that describe morally reprehensible actions or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essor
    -0.75
    iets
    -0.71
     stabilize
    -0.71
    ersion
    -0.71
    aver
    -0.71
    knit
    -0.69
    eding
    -0.66
     chi
    -0.66
    ovember
    -0.66
    hner
    -0.66
    POSITIVE LOGITS
     despicable
    0.88
     hypocrisy
    0.82
     injustice
    0.81
     vile
    0.80
     blasp
    0.79
     slander
    0.78
     deeds
    0.77
     disgusting
    0.75
    ifiable
    0.75
    ly
    0.75
    Act Density 0.099%

    No Known Activations