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

    Neuronpedia

    INDEX
    Explanations

    references to economic concepts and dynamics related to power and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ³
    -0.16
    æij©
    -0.16
    adık
    -0.15
    ddit
    -0.13
    alar
    -0.13
    PID
    -0.13
    jong
    -0.13
     Plantae
    -0.12
    ehler
    -0.12
    ÏĪε
    -0.12
    POSITIVE LOGITS
     power
    1.46
    power
    1.27
     Power
    1.18
    -power
    1.14
    Power
    1.10
     POWER
    1.08
    _power
    1.03
    POWER
    0.98
     powers
    0.96
    (power
    0.95
    Act Density 0.306%

    No Known Activations