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

    Neuronpedia

    INDEX
    Explanations

    expressions of sacrifice

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

    sacrifice and its outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.45
    MGR
    -0.42
    Bree
    -0.41
    MODO
    -0.41
    Sys
    -0.41
     news
    -0.41
     informée
    -0.41
     Weiden
    -0.41
    news
    -0.41
    eb
    -0.41
    POSITIVE LOGITS
     Sacrifice
    1.17
     sacrifice
    1.14
    sacrifice
    1.11
     sacrifices
    1.03
     Sacrific
    0.98
    sacrific
    0.97
     sacrificed
    0.96
     sacrificio
    0.93
     sacrificing
    0.92
     sacrific
    0.91
    Act Density 0.009%

    No Known Activations