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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Exactos
    -0.68
    SequentialGroup
    -0.63
    verständlich
    -0.62
    iestety
    -0.59
    featureID
    -0.59
    setof
    -0.58
    writeFieldEnd
    -0.56
    OGND
    -0.56
    Unfortunately
    -0.55
    しくて
    -0.54
    POSITIVE LOGITS
     nevertheless
    2.19
     nonetheless
    2.17
    Nevertheless
    2.12
     Nevertheless
    2.11
     Nonetheless
    2.10
    Nonetheless
    2.09
    Still
    2.03
     still
    2.00
     Still
    1.96
    それでも
    1.87
    Act Density 0.222%

    No Known Activations