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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating a positive evaluation or assessment of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acco
    -0.15
    称
    -0.15
    à¥Ĥà¤ļ
    -0.15
    ÏĥÏĥ
    -0.14
    ether
    -0.14
     termed
    -0.14
    actal
    -0.14
     buá»Ļc
    -0.14
    pone
    -0.13
    稱
    -0.13
    POSITIVE LOGITS
     having
    0.50
     being
    0.46
    having
    0.38
    being
    0.35
     Having
    0.34
    Having
    0.34
     ayant
    0.31
     sendo
    0.28
     Being
    0.27
    Being
    0.25
    Act Density 0.121%

    No Known Activations