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

    Neuronpedia

    INDEX
    Explanations

    concepts and terms related to reversals or inversions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifice
    -0.17
    lis
    -0.15
    äch
    -0.15
    ÑĢив
    -0.15
    ãģĶãģĸ
    -0.15
    indow
    -0.14
    çľī
    -0.14
    roups
    -0.14
    iken
    -0.14
    çĶļ
    -0.13
    POSITIVE LOGITS
     polarity
    0.27
     direction
    0.27
     engineer
    0.24
    -engine
    0.23
     engineered
    0.23
     engineering
    0.21
     gear
    0.20
    -direction
    0.20
     roles
    0.20
     course
    0.19
    Act Density 0.025%

    No Known Activations