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

    Neuronpedia

    INDEX
    Explanations

    expressions of social interactions and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.44
    parsedMessage
    -0.42
    gbarkeit
    -0.42
     来自
    -0.36
     nakalista
    -0.36
    makeText
    -0.35
     kasarigan
    -0.33
    nerable
    -0.31
     يتيمه
    -0.31
     שוליים
    -0.31
    POSITIVE LOGITS
     nightlife
    0.63
     socializing
    0.63
     entertainment
    0.59
     partying
    0.58
    aarrggbb
    0.57
     socialize
    0.56
    🔕
    0.56
     nightclub
    0.55
     hangout
    0.54
     boredom
    0.53
    Act Density 0.058%

    No Known Activations