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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and planning in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rees
    -0.07
    loh
    -0.07
    ongyang
    -0.06
    asti
    -0.06
    Æ¡
    -0.06
    eree
    -0.06
    uisse
    -0.06
    tae
    -0.06
    657
    -0.06
    ALES
    -0.06
    POSITIVE LOGITS
     abandon
    0.16
     giving
    0.15
     abandoned
    0.14
     give
    0.14
     gave
    0.14
     abandonment
    0.13
     abandoning
    0.13
     Give
    0.13
    give
    0.13
    Give
    0.13
    Act Density 0.067%

    No Known Activations