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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the prefix "pri," particularly in words related to proprietary or private matters

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

    Tokens starting with "Pri"

    np_acts-logits-general · gemini-2.0-flash

    words starting with "pri"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.70
    kuuta
    -0.69
    AutoScaleMode
    -0.64
    ValueGeneration
    -0.59
    awtextra
    -0.59
    VYMaps
    -0.57
    ByVersion
    -0.56
    //
    -0.49
     equidist
    -0.49
    HStack
    -0.47
    POSITIVE LOGITS
    Portale
    0.73
    fromnode
    0.56
     facie
    0.56
    ciple
    0.56
     nationaux
    0.55
    +#+
    0.55
     partenza
    0.55
    MessageTagHelper
    0.55
     stationnement
    0.53
     genoux
    0.52
    Act Density 0.126%

    No Known Activations