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

    Neuronpedia

    INDEX
    Explanations

    formal statements regarding guidelines or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abar
    -0.07
     unle
    -0.06
    ارÙĩ
    -0.06
    _flutter
    -0.06
    aber
    -0.06
    侯
    -0.06
    obb
    -0.06
    .Shared
    -0.05
    umen
    -0.05
     Ste
    -0.05
    POSITIVE LOGITS
     precedence
    0.10
    çŁ
    0.08
    uhe
    0.07
    trak
    0.07
     contradictions
    0.07
    ogne
    0.07
    -vars
    0.07
    _CAPACITY
    0.06
     Conflict
    0.06
     contradiction
    0.06
    Act Density 0.002%

    No Known Activations