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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to specificity or uniqueness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĤ¯
    -0.75
    udi
    -0.72
    clips
    -0.72
    runners
    -0.70
    OIL
    -0.70
     âĨij
    -0.70
    masters
    -0.68
    docs
    -0.68
    flex
    -0.68
    IVERS
    -0.68
    POSITIVE LOGITS
     piece
    1.15
     amount
    1.14
     destination
    1.09
     location
    1.08
     person
    1.06
     target
    1.04
     direction
    1.00
     number
    0.99
     outcome
    0.99
     subset
    0.96
    Act Density 0.102%

    No Known Activations