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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bench
    -0.15
    zure
    -0.15
    UNCH
    -0.15
    yle
    -0.15
     principle
    -0.14
    tor
    -0.14
    ben
    -0.14
     pulp
    -0.14
    anych
    -0.14
     Principle
    -0.14
    POSITIVE LOGITS
    ÏįÏĦε
    0.15
    ahr
    0.15
    readcr
    0.15
    avian
    0.15
    ÑģÑĤÑĢе
    0.15
    med
    0.14
     McGr
    0.14
    weise
    0.14
    Carthy
    0.14
    arParams
    0.14
    Act Density 0.021%

    No Known Activations