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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to personality traits or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to meticulousness and negative behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Annotations
    -0.83
     Bundy
    -0.82
    eer
    -0.79
     Lans
    -0.75
    icides
    -0.75
    olin
    -0.75
     Pell
    -0.73
    rams
    -0.71
    yrim
    -0.71
    rill
    -0.70
    POSITIVE LOGITS
     conscientious
    0.90
     bowel
    0.73
    ortment
    0.71
    urgical
    0.69
     dispos
    0.69
    cientious
    0.68
     object
    0.66
    byter
    0.65
    omal
    0.64
    ullivan
    0.63
    Act Density 0.019%

    No Known Activations