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

    Neuronpedia

    INDEX
    Explanations

    themes related to personal autonomy and control over one's life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylon
    -0.16
    леж
    -0.15
    krv
    -0.15
    imals
    -0.14
    zano
    -0.14
    vious
    -0.14
    dma
    -0.14
    SCR
    -0.14
    743
    -0.14
     pois
    -0.14
    POSITIVE LOGITS
     control
    0.19
     choice
    0.17
    Choice
    0.17
     freedom
    0.17
    eon
    0.17
     Sovere
    0.17
    control
    0.17
    -control
    0.16
    stry
    0.16
     sovereign
    0.16
    Act Density 0.239%

    No Known Activations