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

    Neuronpedia

    INDEX
    Explanations

    phrases related to limits or scope of actions or opinions

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

    "To what extent" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    extent and fullest extent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laikā
    -0.56
     since
    -0.47
     Absicht
    -0.45
     Since
    -0.43
     vistazo
    -0.42
    ACE
    -0.42
    Since
    -0.41
     nélk
    -0.41
    f
    -0.41
    ince
    -0.41
    POSITIVE LOGITS
     extent
    1.56
    extent
    1.22
     detriment
    1.10
     Extent
    1.04
     degree
    0.98
     fullest
    0.97
    ConstraintMaker
    0.94
     CreateTagHelper
    0.92
     chagrin
    0.92
     hilt
    0.81
    Act Density 0.218%

    No Known Activations