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

    Neuronpedia

    INDEX
    Explanations

    questions and responses in conversational contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Alcalde
    -0.53
     للمعارف
    -0.52
     kılıf
    -0.51
     phosphory
    -0.50
    Excerpt
    -0.50
     biotite
    -0.49
     vermelhas
    -0.49
     milliers
    -0.48
     дописавши
    -0.47
     vermelha
    -0.46
    POSITIVE LOGITS
    mergeFrom
    0.75
    makeConstraints
    0.73
     تضيفلها
    0.70
    Personendaten
    0.69
     насељу
    0.66
    رشف
    0.64
    GenerationType
    0.63
    styleType
    0.62
    bootstrapcdn
    0.61
    ContentAlignment
    0.61
    Act Density 0.069%

    No Known Activations