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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate importance or significance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grants
    -0.36
    ✨:
    -0.35
     biscuits
    -0.34
     Biscuits
    -0.34
    Curves
    -0.33
     gar
    -0.33
     cohorts
    -0.33
     totals
    -0.33
     GRANT
    -0.32
    ätzung
    -0.32
    POSITIVE LOGITS
    satunya
    0.62
    şört
    0.59
     nahilalakip
    0.57
     ways
    0.56
     important
    0.53
     poffible
    0.53
    ⓧ
    0.52
     belangrijke
    0.52
     중요
    0.52
     Besonder
    0.51
    Act Density 0.641%

    No Known Activations