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

    Neuronpedia

    INDEX
    Explanations

    references to entities or groups, particularly focused on the subject "we" or "they"

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

    Followed by auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    they/we expressing intent or possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.58
    ipheral
    -0.56
    resher
    -0.55
     Exactos
    -0.55
    клопе
    -0.54
    OTTEN
    -0.53
    UAGE
    -0.53
    audiovisuel
    -0.53
    culable
    -0.53
    MERCIAL
    -0.52
    POSITIVE LOGITS
     want
    0.82
     would
    0.78
     could
    0.74
     will
    0.69
     should
    0.68
     wanted
    0.67
     thought
    0.67
     need
    0.66
     wants
    0.66
     had
    0.66
    Act Density 0.815%

    No Known Activations