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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing indifference or a lack of concern

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

    expressions of indifference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    رشف
    -0.41
     gains
    -0.39
    /*:
    -0.35
     fram
    -0.35
    着一个
    -0.34
    kháu
    -0.34
     Arora
    -0.34
     Gita
    -0.34
     Velas
    -0.34
     NX
    -0.34
    POSITIVE LOGITS
    AndEndTag
    0.62
     Irrelevant
    0.58
    importe
    0.58
     indifferent
    0.57
     quelconque
    0.57
     irrelevant
    0.57
    ardless
    0.56
     indifference
    0.56
    regardless
    0.54
    atever
    0.54
    Act Density 0.012%

    No Known Activations