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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    -0.54
     serem
    -0.44
    ../../
    -0.43
    jss
    -0.40
    切
    -0.39
    止
    -0.38
    прочем
    -0.38
     terem
    -0.37
    ș
    -0.36
    呢
    -0.36
    POSITIVE LOGITS
    MessageTagHelper
    1.00
    ReusableCell
    0.91
     NSCoder
    0.91
    probably
    0.91
     probably
    0.90
    somewhere
    0.87
     somewhere
    0.85
     Probably
    0.84
     prolly
    0.83
    المناصب
    0.83
    Act Density 0.335%

    No Known Activations