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

    Neuronpedia

    INDEX
    Explanations

    references to family dynamics and household interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licit
    -0.16
    raya
    -0.16
     yat
    -0.14
    ayd
    -0.14
    isons
    -0.14
     addCriterion
    -0.14
     lateral
    -0.14
    orthand
    -0.13
     Disqus
    -0.13
    ÙħÙĨت
    -0.13
    POSITIVE LOGITS
     extreme
    0.57
     ends
    0.54
     extrem
    0.50
     extremes
    0.49
     end
    0.47
     Extreme
    0.44
     opposite
    0.42
     Ends
    0.41
    ends
    0.40
    Extreme
    0.40
    Act Density 0.141%

    No Known Activations