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

    Neuronpedia

    INDEX
    Explanations

    references to major historical events and periods, particularly wars and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.59
     InputDecoration
    -0.54
     picioare
    -0.53
    anneer
    -0.50
    IntoConstraints
    -0.49
     argint
    -0.48
     الرياضيه
    -0.48
    ệm
    -0.48
    SourceChecksum
    -0.46
    tedra
    -0.46
    POSITIVE LOGITS
     wartime
    0.49
     Hitler
    0.48
     WWII
    0.47
     Nazi
    0.44
    locaust
    0.44
     Nazis
    0.43
     Holocaust
    0.42
     nazis
    0.42
     War
    0.41
    Diwedd
    0.41
    Act Density 0.244%

    No Known Activations