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

    Neuronpedia

    INDEX
    Explanations

    legal, obligation

    np_max-act · gemini-2.0-flash

    dialogue related to role-playing and character engagement in a narrative context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sentencing
    -0.07
    iance
    -0.07
     arrest
    -0.06
    WE
    -0.06
     SendMessage
    -0.06
    base
    -0.06
     philosopher
    -0.06
     model
    -0.06
     eyes
    -0.06
     arrests
    -0.06
    POSITIVE LOGITS
     kayn
    0.06
     ICU
    0.06
     cargo
    0.06
    \Action
    0.06
    -sem
    0.06
     Pee
    0.06
    luğ
    0.06
     VS
    0.06
     SOCK
    0.06
     chống
    0.06
    Act Density 0.027%

    No Known Activations