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

    Neuronpedia

    INDEX
    Explanations

    terms related to user policies and expected conditions within a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToFit
    -0.16
    obo
    -0.15
     полоÑģ
    -0.15
    amen
    -0.15
    ÙĪاÙĨ
    -0.15
    amar
    -0.14
    thal
    -0.14
    hausen
    -0.14
    edList
    -0.14
    ubern
    -0.14
    POSITIVE LOGITS
    :
    0.20
    *:
    0.14
    +:
    0.14
     Tick
    0.14
     hã
    0.13
    ?:
    0.13
     Orwell
    0.13
    aft
    0.13
     Cron
    0.13
    iec
    0.13
    Act Density 0.105%

    No Known Activations