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

    Neuronpedia

    INDEX
    Explanations

    expressions of freedom and choice in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kle
    -0.18
    akat
    -0.16
    oleÄį
    -0.16
    ikan
    -0.15
    rada
    -0.15
    lag
    -0.14
    adr
    -0.14
    cla
    -0.14
    lez
    -0.14
    lap
    -0.14
    POSITIVE LOGITS
    isse
    0.18
    imbus
    0.15
     Diss
    0.15
    ttl
    0.15
    енÑģ
    0.14
     Tatto
    0.14
    ownload
    0.14
    ewise
    0.14
    ãģĸ
    0.14
    igor
    0.14
    Act Density 0.010%

    No Known Activations