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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence, skill, and the qualities necessary for effective performance or craftsmanship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENCHMARK
    -0.17
    ardy
    -0.16
    ÙĪار
    -0.16
    hesion
    -0.15
     hry
    -0.14
    osti
    -0.14
    esteem
    -0.14
    ilers
    -0.14
     Sentry
    -0.14
    osy
    -0.14
    POSITIVE LOGITS
     intelligence
    0.39
     judgment
    0.36
     judgement
    0.33
     ing
    0.31
     skill
    0.30
     intellect
    0.30
     vision
    0.30
     initiative
    0.29
     wit
    0.28
     skills
    0.28
    Act Density 0.291%

    No Known Activations