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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that suggest hypothetical situations or questions

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

    Followed by "you" after an "If"

    np_acts-logits-general · gemini-2.0-flash

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.59
    Demografie
    -0.57
     eventdata
    -0.54
    EndProject
    -0.49
     felb
    -0.47
    centralwidget
    -0.46
    CHEZ
    -0.46
     مشارکت‌کنندگان
    -0.45
    gwt
    -0.45
     uitzicht
    -0.44
    POSITIVE LOGITS
     you
    1.47
     youre
    1.19
    you
    1.01
     your
    0.92
     você
    0.89
     vous
    0.87
    your
    0.82
    você
    0.79
    您
    0.76
    Você
    0.76
    Act Density 0.078%

    No Known Activations