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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of freedom or phrases associated with free will

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amm
    -0.16
     Baron
    -0.15
    ivo
    -0.15
    py
    -0.15
    atham
    -0.15
    sec
    -0.14
    pic
    -0.14
    ella
    -0.14
    arium
    -0.14
    uss
    -0.14
    POSITIVE LOGITS
    fall
    0.22
    zing
    0.21
    /free
    0.20
    zers
    0.20
     enterprise
    0.19
     lance
    0.19
    zes
    0.19
     free
    0.19
    -wheel
    0.19
     Enterprise
    0.19
    Act Density 0.030%

    No Known Activations