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

    Neuronpedia

    INDEX
    Explanations

    terms related to power and its impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.55
    AISSEE
    -0.54
     يتيمه
    -0.54
    exitRule
    -0.54
    %"),
    -0.54
    +#+
    -0.54
     defaultstate
    -0.53
    WriteBarrier
    -0.53
    findpost
    -0.52
     slop
    -0.51
    POSITIVE LOGITS
     powerful
    1.45
    Powerful
    1.35
    powerful
    1.34
     Powerful
    1.30
     power
    1.22
     poderosa
    1.13
     poderoso
    1.13
    power
    1.12
     poderos
    1.09
     puissante
    1.09
    Act Density 0.378%

    No Known Activations