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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to power and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uco
    -0.17
    ÅĻet
    -0.17
    onian
    -0.16
    orum
    -0.15
    داÙħ
    -0.15
    ê
    -0.15
    sez
    -0.15
    agal
    -0.14
    isma
    -0.14
    alian
    -0.14
    POSITIVE LOGITS
     powerful
    0.30
    /power
    0.28
    power
    0.26
     Powerful
    0.25
     potent
    0.24
     power
    0.23
    powers
    0.23
     mạnh
    0.22
    (power
    0.21
    -strong
    0.21
    Act Density 0.079%

    No Known Activations