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

    Neuronpedia

    INDEX
    Explanations

    mentions of exceptions or special cases in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beth
    -0.15
    bert
    -0.15
    upp
    -0.15
    asi
    -0.15
    amer
    -0.14
    apsed
    -0.14
    Ñģли
    -0.13
    efon
    -0.13
     ashamed
    -0.13
     Round
    -0.13
    POSITIVE LOGITS
    ively
    0.18
    ìĤ¬íķŃ
    0.16
    (Exception
    0.15
     cumulative
    0.15
    aneous
    0.15
     circumstances
    0.15
     Cum
    0.14
    üny
    0.14
    ality
    0.14
    nelle
    0.14
    Act Density 0.021%

    No Known Activations