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

    Neuronpedia

    INDEX
    Explanations

    references to concepts of freedom and restrictions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctest
    -0.15
    ãİ
    -0.14
    ÙĨج
    -0.14
    itag
    -0.14
    alama
    -0.14
    Ñĩин
    -0.13
    åĺĽ
    -0.13
     sometimes
    -0.13
    erap
    -0.13
    852
    -0.13
    POSITIVE LOGITS
     unlikely
    0.32
     unless
    0.30
    unlikely
    0.28
    unless
    0.24
     Likely
    0.24
     likely
    0.23
     likelihood
    0.22
     Unless
    0.22
    likely
    0.21
    Unless
    0.20
    Act Density 0.165%

    No Known Activations