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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditionality or exceptions, particularly focusing on the term "regardless of"

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

    regardless of context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreExecute
    -0.44
     taskId
    -0.42
     refreshToken
    -0.41
    InputTagHelper
    -0.41
     paro
    -0.41
     pellic
    -0.40
     newData
    -0.40
    enderror
    -0.40
     onPostExecute
    -0.40
    readlines
    -0.39
    POSITIVE LOGITS
     quaisquer
    0.66
     whether
    0.65
     Мексичка
    0.63
     WHETHER
    0.59
    atever
    0.58
     regardless
    0.57
     désolés
    0.57
     apapun
    0.56
     quelconque
    0.56
    eachtet
    0.56
    Act Density 0.011%

    No Known Activations