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

    Neuronpedia

    INDEX
    Explanations

    references to selection and choice, particularly in contexts of curation or preference

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

    picked or selected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.49
     utafitiHapana
    -0.40
    adaptiveStyles
    -0.38
     Monument
    -0.38
    Hochspringen
    -0.37
     hustle
    -0.37
     verksamhet
    -0.35
    GraphicsUnit
    -0.34
     alvor
    -0.33
     kalian
    -0.32
    POSITIVE LOGITS
    picked
    0.90
     selected
    0.77
     chosen
    0.72
    chosen
    0.71
    selected
    0.70
     ausgewä
    0.68
     SELECTED
    0.68
     picked
    0.67
    Selected
    0.65
    厳選
    0.65
    Act Density 0.014%

    No Known Activations