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

    Neuronpedia

    INDEX
    Explanations

    references to responsibility and support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     altogether
    -0.25
     already
    -0.21
    uch
    -0.19
     oft
    -0.18
     often
    -0.17
    ally
    -0.17
     entirety
    -0.17
    already
    -0.16
     repeatedly
    -0.16
     everyday
    -0.16
    POSITIVE LOGITS
     whenever
    0.26
     Whenever
    0.22
    Whenever
    0.21
     ALWAYS
    0.16
    YRO
    0.15
     irgend
    0.15
    à¸Ļà¸Ķ
    0.15
    cky
    0.15
    rowable
    0.14
     wherever
    0.14
    Act Density 0.182%

    No Known Activations