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

    Neuronpedia

    INDEX
    Explanations

    occurrences of possessive pronouns and possessive constructs

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

    Followed by specific French words

    np_acts-logits-general · gemini-2.0-flash

    historical text fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    égard
    -0.71
    esercito
    -0.69
    agissait
    -0.66
    Égypte
    -0.65
    Egypte
    -0.65
     testSet
    -0.64
    commut
    -0.64
    botto
    -0.64
    voici
    -0.62
    rdom
    -0.62
    POSITIVE LOGITS
     ExecuteAsync
    0.61
     houſe
    0.60
     occaf
    0.59
     ambush
    0.59
     Iri
    0.58
     unſ
    0.58
     abſ
    0.58
     obſ
    0.58
     analogy
    0.57
     attaque
    0.57
    Act Density 0.033%

    No Known Activations