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

    Neuronpedia

    INDEX
    Explanations

    the word "of" as it denotes relationships or connections within a context

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

    direction of location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     full
    -0.42
     extra
    -0.35
     Plenum
    -0.34
    Trả
    -0.31
    full
    -0.31
     Suara
    -0.31
     best
    -0.30
    GetInstance
    -0.30
     special
    -0.30
     iné
    -0.30
    POSITIVE LOGITS
    neath
    0.70
     ویکی‌پدی
    0.68
    principalColumn
    0.67
     laſſen
    0.66
    IntoConstraints
    0.66
     betweenstory
    0.65
     Above
    0.65
    letoe
    0.65
    posedge
    0.65
    HostException
    0.64
    Act Density 0.014%

    No Known Activations