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

    Neuronpedia

    INDEX
    Explanations

    phrases related to skills and abilities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific skills and competencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eviction
    -0.94
     mosqu
    -0.89
     closure
    -0.87
     closures
    -0.83
     motel
    -0.82
     insurer
    -0.82
     evacuation
    -0.82
     cancellation
    -0.81
    soType
    -0.80
     reopened
    -0.78
    POSITIVE LOGITS
     proficiency
    1.50
     mastery
    1.50
     mastering
    1.50
     mastered
    1.47
     skills
    1.46
     skill
    1.45
     talent
    1.44
     talents
    1.41
    digy
    1.38
     proficient
    1.36
    Act Density 0.990%

    No Known Activations