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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases that describe various qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oste
    -0.17
    iqueta
    -0.16
    ateria
    -0.15
    eniable
    -0.15
    opher
    -0.15
    buquerque
    -0.15
    ابر
    -0.15
    èĢħçļĦ
    -0.14
    itors
    -0.14
    Injected
    -0.14
    POSITIVE LOGITS
     inspiration
    0.22
     menace
    0.22
     victim
    0.20
    verse
    0.19
     magnet
    0.18
     perfection
    0.18
     rarity
    0.18
     frequent
    0.18
     walking
    0.17
     anomaly
    0.17
    Act Density 0.126%

    No Known Activations