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

    Neuronpedia

    INDEX
    Explanations

    expressions of positivity and gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antis
    -0.15
    antry
    -0.15
     enduring
    -0.15
     personalities
    -0.14
    ant
    -0.13
     Bench
    -0.13
     -
    -0.13
     precisely
    -0.13
    __
    -0.13
    65
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.23
    redi
    0.16
    еÑĢин
    0.16
     å¹³æĸ¹
    0.16
    639
    0.15
     Sesso
    0.15
    rl
    0.15
     УкÑĢаÑĹн
    0.15
    oha
    0.14
    042
    0.14
    Act Density 0.174%

    No Known Activations