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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uniqueness and differentiation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.59
    المشاركات
    -0.54
     blackmail
    -0.52
     المعيارى
    -0.45
     pool
    -0.43
     forceps
    -0.42
     Niro
    -0.42
    SceneManagement
    -0.41
     Pool
    -0.41
     Plastic
    -0.41
    POSITIVE LOGITS
     differentiate
    0.74
     differentiating
    0.72
     differentiates
    0.69
     distinctive
    0.68
     wyróż
    0.66
     uniqueness
    0.66
     distinguishing
    0.64
     diferencia
    0.62
     diferenci
    0.62
     difference
    0.61
    Act Density 0.016%

    No Known Activations