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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and their relationships in context

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

    names followed by action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     együtt
    -0.68
    combined
    -0.66
     combined
    -0.63
     samenwerking
    -0.61
     interaction
    -0.57
    interaction
    -0.57
    Combined
    -0.56
     samarbeid
    -0.56
     interactions
    -0.54
     Combined
    -0.53
    POSITIVE LOGITS
    PullParser
    0.66
    astify
    0.66
    GEBURTSDATUM
    0.65
    исленность
    0.59
    ">//
    0.57
    новништво
    0.52
     reciproc
    0.51
    Дереккөздер
    0.51
    contentLoaded
    0.50
    ModelSerializer
    0.50
    Act Density 0.119%

    No Known Activations