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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expectations and accountability from elected representatives

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

    possessive pronouns and their nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bilan
    -0.37
    勿
    -0.36
    ษา
    -0.35
    hradun
    -0.35
     Lausanne
    -0.35
    actual
    -0.35
    äume
    -0.34
    ursa
    -0.34
    aderas
    -0.34
    ansen
    -0.34
    POSITIVE LOGITS
     your
    1.41
    Your
    1.09
    your
    1.06
     votre
    1.02
     vostra
    0.97
     Your
    0.97
     iyong
    0.85
     вашего
    0.85
    Ваш
    0.84
     Votre
    0.83
    Act Density 0.020%

    No Known Activations