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

    Neuronpedia

    INDEX
    Explanations

    phrases characterized by comparisons or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acco
    -0.17
    ether
    -0.14
    ÏĥÏĥ
    -0.14
    pone
    -0.14
    à¥Ĥà¤ļ
    -0.13
    Opts
    -0.13
     buá»Ļc
    -0.13
    aron
    -0.13
     termed
    -0.13
    称
    -0.13
    POSITIVE LOGITS
     having
    0.56
     being
    0.49
    having
    0.44
    being
    0.41
     Having
    0.40
    Having
    0.39
     ayant
    0.36
     sendo
    0.31
     Being
    0.30
    Being
    0.29
    Act Density 0.113%

    No Known Activations