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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe features or qualities of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    099
    -0.15
    Ãły
    -0.15
    409
    -0.15
    imes
    -0.14
    089
    -0.14
    кÑĤи
    -0.13
     Forbidden
    -0.13
    049
    -0.13
    irable
    -0.13
    razier
    -0.13
    POSITIVE LOGITS
    rey
    0.16
     lots
    0.13
     Spread
    0.13
     Kart
    0.13
    lix
    0.13
    baum
    0.13
    leich
    0.13
    bole
    0.13
     repeat
    0.12
    ften
    0.12
    Act Density 0.089%

    No Known Activations