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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to neutrality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tradição
    -0.51
     tradición
    -0.51
     kaldı
    -0.48
     Vordergrund
    -0.47
    IBOutlet
    -0.46
     Verantwortung
    -0.45
     romántica
    -0.44
    guiente
    -0.43
     afecto
    -0.43
     Italij
    -0.42
    POSITIVE LOGITS
     wool
    0.75
     Rule
    0.69
     Gray
    0.68
    Gray
    0.68
    Rule
    0.68
     gray
    0.67
     GRAY
    0.63
    gray
    0.62
     Wool
    0.60
     Rules
    0.60
    Act Density 0.189%

    No Known Activations