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

    Neuronpedia

    INDEX
    Explanations

    references to political processes and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words or phrases indicating causality

    np_acts-logits-general · gemini-2.0-flash

    because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raiſ
    -0.49
    transQ
    -0.48
    ientras
    -0.48
     Kapol
    -0.48
    ambién
    -0.44
    Preference
    -0.44
    antaranya
    -0.43
     panoramique
    -0.43
     Commentaires
    -0.43
    CommandType
    -0.42
    POSITIVE LOGITS
     because
    1.41
    because
    1.20
     porque
    1.20
     puisque
    1.17
    因为
    1.10
     karena
    1.10
     omdat
    1.09
     ponieważ
    1.08
     puisqu
    1.08
    因為
    1.06
    Act Density 0.812%

    No Known Activations