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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical power dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usan
    -0.18
    ilen
    -0.17
    lero
    -0.16
    å¢ĥ
    -0.16
    rava
    -0.14
    affer
    -0.13
    vala
    -0.13
    _tol
    -0.13
    ocrat
    -0.13
    utch
    -0.13
    POSITIVE LOGITS
     powers
    0.45
     Powers
    0.39
    powers
    0.37
     power
    0.34
    power
    0.29
    -power
    0.29
     super
    0.28
    Power
    0.27
     Power
    0.27
     POWER
    0.25
    Act Density 0.099%

    No Known Activations