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

    Neuronpedia

    INDEX
    Explanations

    references to required skills or knowledge for various tasks or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tslint
    -0.18
    alis
    -0.16
     Excellence
    -0.16
    stav
    -0.16
    oras
    -0.15
     ineff
    -0.15
    charset
    -0.15
     вик
    -0.14
    esture
    -0.14
    اÙĪر
    -0.14
    POSITIVE LOGITS
     skills
    0.27
     expertise
    0.25
     knowledge
    0.24
    knowledge
    0.23
    skills
    0.22
    Skills
    0.22
     skill
    0.22
     skilled
    0.20
     Skills
    0.20
    skill
    0.19
    Act Density 0.175%

    No Known Activations