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

    Neuronpedia

    INDEX
    Explanations

    articles and adjectives indicating descriptions or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MAG
    -0.19
     Castillo
    -0.15
    ↵↵
    -0.15
     Gad
    -0.15
    ursal
    -0.15
    ëĵĿ
    -0.14
    ÏĦÏī
    -0.14
    urette
    -0.14
     nackte
    -0.14
    ollah
    -0.14
    POSITIVE LOGITS
     placeholder
    0.24
    placeholder
    0.19
     digit
    0.16
     list
    0.15
     suit
    0.15
    Placeholder
    0.15
     beta
    0.15
    	placeholder
    0.15
    ÏģοÏħ
    0.14
     guest
    0.14
    Act Density 0.014%

    No Known Activations