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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions indicating relationships or connections

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

    pronouns and prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.65
     nonUne
    -0.56
     Biôgrafia
    -0.56
     dezelve
    -0.52
    othelioma
    -0.51
    EndInit
    -0.50
    Espèce
    -0.49
    ocardium
    -0.48
    évaluateur
    -0.47
    таратура
    -0.47
    POSITIVE LOGITS
     himself
    0.53
     him
    0.53
     them
    0.46
     us
    0.44
     her
    0.42
    makeText
    0.41
     his
    0.40
     Baus
    0.40
     it
    0.40
     herself
    0.40
    Act Density 0.003%

    No Known Activations