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

    Neuronpedia

    INDEX
    Explanations

    references to political leaders and positions

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

    titles of leaders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /#{
    -0.37
     adventurer
    -0.37
    Captain
    -0.36
     Captain
    -0.35
     Xiao
    -0.35
     TIL
    -0.35
    ungsbedingungen
    -0.35
    ！”
    -0.34
    noindent
    -0.34
     Tanya
    -0.34
    POSITIVE LOGITS
     presidents
    1.13
     Presidents
    1.03
     governors
    0.98
    Presidents
    0.97
     fathers
    0.90
     CEOs
    0.85
     mayors
    0.85
     emperors
    0.84
     Governors
    0.84
     chiefs
    0.81
    Act Density 0.026%

    No Known Activations