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

    Neuronpedia

    INDEX
    Explanations

    strong expressions of determination and commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Willingness to do anything/"go to" lengths

    np_acts-logits-general · gemini-2.0-flash

    do anything or sacrifice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.61
     autorytatywna
    -0.61
    contentLoaded
    -0.54
    maxcdn
    -0.53
     invokingState
    -0.51
     jā
    -0.47
     felé
    -0.45
    loč
    -0.45
    كمة
    -0.44
    TestingModule
    -0.44
    POSITIVE LOGITS
     Sacrific
    0.97
     sacrifice
    0.97
     sacrifices
    0.96
     sacrificing
    0.94
     anything
    0.94
     sacrificed
    0.93
    Anything
    0.93
    anything
    0.92
     ANYTHING
    0.92
     Anything
    0.92
    Act Density 0.147%

    No Known Activations