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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power dynamics and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adık
    -0.19
    Pid
    -0.16
    olet
    -0.14
     Pier
    -0.14
    rema
    -0.14
    fgang
    -0.14
    ůj
    -0.14
    xda
    -0.14
    ãĥ¼ãĥ³
    -0.14
     Parenthood
    -0.14
    POSITIVE LOGITS
     power
    1.25
    power
    1.09
     Power
    1.08
    -power
    1.02
    Power
    1.00
     POWER
    0.97
    _power
    0.94
     powers
    0.89
    .power
    0.88
    POWER
    0.87
    Act Density 0.336%

    No Known Activations