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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political power dynamics and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adık
    -0.15
    icos
    -0.15
    æij©
    -0.14
    èī
    -0.13
     Plantae
    -0.13
    jsonp
    -0.13
    ehler
    -0.13
    uard
    -0.12
    alar
    -0.12
     Downs
    -0.12
    POSITIVE LOGITS
     power
    1.16
    power
    1.02
    -power
    0.91
     Power
    0.89
     POWER
    0.86
    Power
    0.85
    _power
    0.80
     powers
    0.80
    POWER
    0.77
     poder
    0.75
    Act Density 0.347%

    No Known Activations