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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a viewpoint or perspective

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

    introducing a viewpoint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     McCulloch
    -0.33
    怎么办
    -0.33
     circ
    -0.32
    artic
    -0.32
     coc
    -0.32
    cauc
    -0.32
    sandbox
    -0.31
    inim
    -0.30
    ifoli
    -0.30
    クシー
    -0.30
    POSITIVE LOGITS
     standpoint
    0.70
     pinulongan
    0.68
     segi
    0.59
    Về
    0.59
    acamata
    0.58
    CloseOperation
    0.54
     względem
    0.54
     perspectiva
    0.54
    Portail
    0.52
    的角度
    0.52
    Act Density 0.012%

    No Known Activations