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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing obligation, possibility, and general statements about actions or feelings

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

    while followed by auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➯
    -0.68
    InputTagHelper
    -0.53
    */),
    -0.49
    !*\
    -0.47
     FormData
    -0.44
     propOrder
    -0.44
     SwitchCompat
    -0.43
     kohdetta
    -0.41
     disambiguazione
    -0.41
    });*/
    -0.40
    POSITIVE LOGITS
     spesa
    0.50
    MigrationBuilder
    0.49
     preghiera
    0.48
    While
    0.47
     ciertamente
    0.47
    Whilst
    0.45
    Пока
    0.44
    hile
    0.44
    แห่ง
    0.43
    atyw
    0.43
    Act Density 0.041%

    No Known Activations