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

    Neuronpedia

    INDEX
    Explanations

    terms related to assistance or support in various contexts

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

    help and assist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meille
    -0.50
     menemp
    -0.45
     zelve
    -0.44
     soumettre
    -0.43
     beroep
    -0.43
     opleiding
    -0.41
     egentligen
    -0.41
     leçons
    -0.41
     llantas
    -0.40
     cejas
    -0.40
    POSITIVE LOGITS
     Assist
    0.66
     assisting
    0.63
     assist
    0.59
    Assist
    0.59
    verifyException
    0.56
    assist
    0.56
     helpers
    0.55
    tagext
    0.54
    Helping
    0.54
     Helping
    0.53
    Act Density 0.014%

    No Known Activations