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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection and enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ISNI
    -0.65
    verwijspagina
    -0.64
     مشين
    -0.62
    
    -0.61
    ="@+
    -0.57
    期刊论文
    -0.56
     milliers
    -0.56
    Referencie
    -0.55
    illoma
    -0.54
     altrimenti
    -0.54
    POSITIVE LOGITS
     hearing
    0.86
     seeing
    0.68
     surprises
    0.68
     tanken
    0.62
    ee
    0.62
     watching
    0.62
    Dislikes
    0.61
    eee
    0.61
     simplicity
    0.60
    eeee
    0.59
    Act Density 0.172%

    No Known Activations