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

    Neuronpedia

    INDEX
    Explanations

    positive expressions and greetings related to social interactions

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

    I statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.73
     queſta
    -0.69
     мәкал
    -0.69
     '\\;'
    -0.67
    XmlAccessType
    -0.67
     propOrder
    -0.65
     increí
    -0.65
    存于互联网档案馆
    -0.64
     incrí
    -0.63
    featureID
    -0.63
    POSITIVE LOGITS
     also
    0.39
     Aw
    0.37
     Ar
    0.37
     I
    0.35
     signed
    0.34
    Also
    0.33
    also
    0.32
    Ar
    0.32
    wär
    0.32
     Also
    0.31
    Act Density 0.009%

    No Known Activations