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

    Neuronpedia

    INDEX
    Explanations

    concepts related to tolerance, intolerance, and inclusive dialogue

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

    acceptance and harmony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gef
    -0.46
     Operating
    -0.40
    Gef
    -0.39
    脚注
    -0.39
     knack
    -0.39
     الميل
    -0.39
     aumentando
    -0.38
    醉
    -0.37
    styleUrls
    -0.37
     UNIX
    -0.37
    POSITIVE LOGITS
     tolerancia
    0.70
    tolerance
    0.66
     tolerance
    0.66
    tolerant
    0.65
    verwijspagina
    0.63
     peaceful
    0.63
    peaceful
    0.63
     tolerant
    0.63
     Tolerance
    0.63
     peace
    0.60
    Act Density 0.058%

    No Known Activations