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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional language indicating vulnerability or pain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SizeMode
    -0.65
     мәгълү
    -0.59
    endaftaran
    -0.58
    ='"+
    -0.57
     "{\"
    -0.57
     &___
    -0.56
    antMatchers
    -0.51
    isEqualTo
    -0.50
     Poole
    -0.48
    くださった
    -0.48
    POSITIVE LOGITS
    ✭✭
    0.74
     дописавши
    0.71
    دانشنامهٔ
    0.67
     '\\;'
    0.62
    ViewImports
    0.61
    󠁣
    0.55
    Specifiche
    0.54
     magasiner
    0.54
     propOrder
    0.54
    Ligações
    0.54
    Act Density 0.053%

    No Known Activations